* and per-CPU runqueues. Cleanups and useful suggestions
* by Davide Libenzi, preemptible kernel bits by Robert Love.
* 2003-09-03 Interactivity tuning by Con Kolivas.
+ * 2004-04-02 Scheduler domains code by Nick Piggin
*/
#include <linux/mm.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
+#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/security.h>
#include <linux/notifier.h>
+#include <linux/profile.h>
#include <linux/suspend.h>
+#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/smp.h>
+#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
+#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
-
-#ifdef CONFIG_NUMA
-#define cpu_to_node_mask(cpu) node_to_cpumask(cpu_to_node(cpu))
-#else
-#define cpu_to_node_mask(cpu) (cpu_online_map)
-#endif
+#include <linux/seq_file.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/acct.h>
+#include <linux/kprobes.h>
+#include <asm/tlb.h>
+
+#include <asm/unistd.h>
+#include <linux/vs_context.h>
+#include <linux/vs_cvirt.h>
+#include <linux/vs_sched.h>
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
#define USER_PRIO(p) ((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
-#define AVG_TIMESLICE (MIN_TIMESLICE + ((MAX_TIMESLICE - MIN_TIMESLICE) *\
- (MAX_PRIO-1-NICE_TO_PRIO(0))/(MAX_USER_PRIO - 1)))
/*
* Some helpers for converting nanosecond timing to jiffy resolution
/*
* These are the 'tuning knobs' of the scheduler:
*
- * Minimum timeslice is 10 msecs, default timeslice is 100 msecs,
- * maximum timeslice is 200 msecs. Timeslices get refilled after
- * they expire.
+ * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
+ * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
+ * Timeslices get refilled after they expire.
*/
-#define MIN_TIMESLICE ( 10 * HZ / 1000)
-#define MAX_TIMESLICE (200 * HZ / 1000)
+#define MIN_TIMESLICE max(5 * HZ / 1000, 1)
+#define DEF_TIMESLICE (100 * HZ / 1000)
#define ON_RUNQUEUE_WEIGHT 30
#define CHILD_PENALTY 95
#define PARENT_PENALTY 100
#define PRIO_BONUS_RATIO 25
#define MAX_BONUS (MAX_USER_PRIO * PRIO_BONUS_RATIO / 100)
#define INTERACTIVE_DELTA 2
-#define MAX_SLEEP_AVG (AVG_TIMESLICE * MAX_BONUS)
+#define MAX_SLEEP_AVG (DEF_TIMESLICE * MAX_BONUS)
#define STARVATION_LIMIT (MAX_SLEEP_AVG)
#define NS_MAX_SLEEP_AVG (JIFFIES_TO_NS(MAX_SLEEP_AVG))
-#define NODE_THRESHOLD 125
-#define CREDIT_LIMIT 100
/*
* If a task is 'interactive' then we reinsert it in the active
(NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \
MAX_SLEEP_AVG)
+#define GRANULARITY (10 * HZ / 1000 ? : 1)
+
#ifdef CONFIG_SMP
-#define TIMESLICE_GRANULARITY(p) (MIN_TIMESLICE * \
+#define TIMESLICE_GRANULARITY(p) (GRANULARITY * \
(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
num_online_cpus())
#else
-#define TIMESLICE_GRANULARITY(p) (MIN_TIMESLICE * \
+#define TIMESLICE_GRANULARITY(p) (GRANULARITY * \
(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)))
#endif
(v1) * (v2_max) / (v1_max)
#define DELTA(p) \
- (SCALE(TASK_NICE(p), 40, MAX_USER_PRIO*PRIO_BONUS_RATIO/100) + \
+ (SCALE(TASK_NICE(p) + 20, 40, MAX_BONUS) - 20 * MAX_BONUS / 40 + \
INTERACTIVE_DELTA)
#define TASK_INTERACTIVE(p) \
(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))
-#define HIGH_CREDIT(p) \
- ((p)->interactive_credit > CREDIT_LIMIT)
-
-#define LOW_CREDIT(p) \
- ((p)->interactive_credit < -CREDIT_LIMIT)
-
#define TASK_PREEMPTS_CURR(p, rq) \
((p)->prio < (rq)->curr->prio)
/*
- * BASE_TIMESLICE scales user-nice values [ -20 ... 19 ]
- * to time slice values.
+ * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
+ * to time slice values: [800ms ... 100ms ... 5ms]
*
* The higher a thread's priority, the bigger timeslices
* it gets during one round of execution. But even the lowest
* priority thread gets MIN_TIMESLICE worth of execution time.
- *
- * task_timeslice() is the interface that is used by the scheduler.
*/
-#define BASE_TIMESLICE(p) (MIN_TIMESLICE + \
- ((MAX_TIMESLICE - MIN_TIMESLICE) * \
- (MAX_PRIO-1 - (p)->static_prio) / (MAX_USER_PRIO-1)))
+#define SCALE_PRIO(x, prio) \
+ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)
-static inline unsigned int task_timeslice(task_t *p)
+static unsigned int task_timeslice(task_t *p)
{
- return BASE_TIMESLICE(p);
+ if (p->static_prio < NICE_TO_PRIO(0))
+ return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
+ else
+ return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
}
+#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \
+ < (long long) (sd)->cache_hot_time)
/*
* These are the runqueue data structures:
typedef struct runqueue runqueue_t;
struct prio_array {
- int nr_active;
+ unsigned int nr_active;
unsigned long bitmap[BITMAP_SIZE];
struct list_head queue[MAX_PRIO];
};
*/
struct runqueue {
spinlock_t lock;
+
+ /*
+ * nr_running and cpu_load should be in the same cacheline because
+ * remote CPUs use both these fields when doing load calculation.
+ */
+ unsigned long nr_running;
+#ifdef CONFIG_SMP
+ unsigned long cpu_load[3];
+#endif
unsigned long long nr_switches;
- unsigned long nr_running, expired_timestamp, nr_uninterruptible,
- timestamp_last_tick;
+
+ /*
+ * This is part of a global counter where only the total sum
+ * over all CPUs matters. A task can increase this counter on
+ * one CPU and if it got migrated afterwards it may decrease
+ * it on another CPU. Always updated under the runqueue lock:
+ */
+ unsigned long nr_uninterruptible;
+
+ unsigned long expired_timestamp;
+ unsigned long long timestamp_last_tick;
task_t *curr, *idle;
struct mm_struct *prev_mm;
prio_array_t *active, *expired, arrays[2];
- int best_expired_prio, prev_cpu_load[NR_CPUS];
-#ifdef CONFIG_NUMA
- atomic_t *node_nr_running;
- int prev_node_load[MAX_NUMNODES];
-#endif
+ int best_expired_prio;
+ atomic_t nr_iowait;
+
+#ifdef CONFIG_SMP
+ struct sched_domain *sd;
+
+ /* For active balancing */
+ int active_balance;
+ int push_cpu;
+
task_t *migration_thread;
struct list_head migration_queue;
+ int cpu;
+#endif
+#ifdef CONFIG_VSERVER_HARDCPU
+ struct list_head hold_queue;
+ int idle_tokens;
+#endif
- atomic_t nr_iowait;
+#ifdef CONFIG_SCHEDSTATS
+ /* latency stats */
+ struct sched_info rq_sched_info;
+
+ /* sys_sched_yield() stats */
+ unsigned long yld_exp_empty;
+ unsigned long yld_act_empty;
+ unsigned long yld_both_empty;
+ unsigned long yld_cnt;
+
+ /* schedule() stats */
+ unsigned long sched_switch;
+ unsigned long sched_cnt;
+ unsigned long sched_goidle;
+
+ /* try_to_wake_up() stats */
+ unsigned long ttwu_cnt;
+ unsigned long ttwu_local;
+#endif
};
static DEFINE_PER_CPU(struct runqueue, runqueues);
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
+#define for_each_domain(cpu, domain) \
+for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
+
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-extern unsigned long __scheduling_functions_start_here;
-extern unsigned long __scheduling_functions_end_here;
-const unsigned long scheduling_functions_start_here =
- (unsigned long)&__scheduling_functions_start_here;
-const unsigned long scheduling_functions_end_here =
- (unsigned long)&__scheduling_functions_end_here;
-
-/*
- * Default context-switch locking:
- */
#ifndef prepare_arch_switch
-# define prepare_arch_switch(rq, next) do { } while (0)
-# define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock)
-# define task_running(rq, p) ((rq)->curr == (p))
+# define prepare_arch_switch(next) do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev) do { } while (0)
#endif
-#ifdef CONFIG_NUMA
-
-/*
- * Keep track of running tasks.
- */
-
-static atomic_t node_nr_running[MAX_NUMNODES] ____cacheline_maxaligned_in_smp =
- {[0 ...MAX_NUMNODES-1] = ATOMIC_INIT(0)};
-
-static inline void nr_running_init(struct runqueue *rq)
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline int task_running(runqueue_t *rq, task_t *p)
{
- rq->node_nr_running = &node_nr_running[0];
+ return rq->curr == p;
}
-static inline void nr_running_inc(runqueue_t *rq)
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
{
- atomic_inc(rq->node_nr_running);
- rq->nr_running++;
}
-static inline void nr_running_dec(runqueue_t *rq)
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
{
- atomic_dec(rq->node_nr_running);
- rq->nr_running--;
+#ifdef CONFIG_DEBUG_SPINLOCK
+ /* this is a valid case when another task releases the spinlock */
+ rq->lock.owner = current;
+#endif
+ spin_unlock_irq(&rq->lock);
}
-__init void node_nr_running_init(void)
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+static inline int task_running(runqueue_t *rq, task_t *p)
{
- int i;
-
- for (i = 0; i < NR_CPUS; i++) {
- if (cpu_possible(i))
- cpu_rq(i)->node_nr_running =
- &node_nr_running[cpu_to_node(i)];
- }
+#ifdef CONFIG_SMP
+ return p->oncpu;
+#else
+ return rq->curr == p;
+#endif
}
-#else /* !CONFIG_NUMA */
-
-# define nr_running_init(rq) do { } while (0)
-# define nr_running_inc(rq) do { (rq)->nr_running++; } while (0)
-# define nr_running_dec(rq) do { (rq)->nr_running--; } while (0)
+static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+{
+#ifdef CONFIG_SMP
+ /*
+ * We can optimise this out completely for !SMP, because the
+ * SMP rebalancing from interrupt is the only thing that cares
+ * here.
+ */
+ next->oncpu = 1;
+#endif
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ spin_unlock_irq(&rq->lock);
+#else
+ spin_unlock(&rq->lock);
+#endif
+}
-#endif /* CONFIG_NUMA */
+static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+{
+#ifdef CONFIG_SMP
+ /*
+ * After ->oncpu is cleared, the task can be moved to a different CPU.
+ * We must ensure this doesn't happen until the switch is completely
+ * finished.
+ */
+ smp_wmb();
+ prev->oncpu = 0;
+#endif
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
/*
* task_rq_lock - lock the runqueue a given task resides on and disable
* explicitly disabling preemption.
*/
static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
+ __acquires(rq->lock)
{
struct runqueue *rq;
}
static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
+ __releases(rq->lock)
{
spin_unlock_irqrestore(&rq->lock, *flags);
}
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * bump this up when changing the output format or the meaning of an existing
+ * format, so that tools can adapt (or abort)
+ */
+#define SCHEDSTAT_VERSION 12
+
+static int show_schedstat(struct seq_file *seq, void *v)
+{
+ int cpu;
+
+ seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
+ seq_printf(seq, "timestamp %lu\n", jiffies);
+ for_each_online_cpu(cpu) {
+ runqueue_t *rq = cpu_rq(cpu);
+#ifdef CONFIG_SMP
+ struct sched_domain *sd;
+ int dcnt = 0;
+#endif
+
+ /* runqueue-specific stats */
+ seq_printf(seq,
+ "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu",
+ cpu, rq->yld_both_empty,
+ rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt,
+ rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
+ rq->ttwu_cnt, rq->ttwu_local,
+ rq->rq_sched_info.cpu_time,
+ rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);
+
+ seq_printf(seq, "\n");
+
+#ifdef CONFIG_SMP
+ /* domain-specific stats */
+ preempt_disable();
+ for_each_domain(cpu, sd) {
+ enum idle_type itype;
+ char mask_str[NR_CPUS];
+
+ cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
+ seq_printf(seq, "domain%d %s", dcnt++, mask_str);
+ for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
+ itype++) {
+ seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu",
+ sd->lb_cnt[itype],
+ sd->lb_balanced[itype],
+ sd->lb_failed[itype],
+ sd->lb_imbalance[itype],
+ sd->lb_gained[itype],
+ sd->lb_hot_gained[itype],
+ sd->lb_nobusyq[itype],
+ sd->lb_nobusyg[itype]);
+ }
+ seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
+ sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
+ sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
+ sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
+ sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
+ }
+ preempt_enable();
+#endif
+ }
+ return 0;
+}
+
+static int schedstat_open(struct inode *inode, struct file *file)
+{
+ unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
+ char *buf = kmalloc(size, GFP_KERNEL);
+ struct seq_file *m;
+ int res;
+
+ if (!buf)
+ return -ENOMEM;
+ res = single_open(file, show_schedstat, NULL);
+ if (!res) {
+ m = file->private_data;
+ m->buf = buf;
+ m->size = size;
+ } else
+ kfree(buf);
+ return res;
+}
+
+struct file_operations proc_schedstat_operations = {
+ .open = schedstat_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+# define schedstat_inc(rq, field) do { (rq)->field++; } while (0)
+# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0)
+#else /* !CONFIG_SCHEDSTATS */
+# define schedstat_inc(rq, field) do { } while (0)
+# define schedstat_add(rq, field, amt) do { } while (0)
+#endif
+
/*
* rq_lock - lock a given runqueue and disable interrupts.
*/
static inline runqueue_t *this_rq_lock(void)
+ __acquires(rq->lock)
{
runqueue_t *rq;
return rq;
}
-static inline void rq_unlock(runqueue_t *rq)
+#ifdef CONFIG_SCHEDSTATS
+/*
+ * Called when a process is dequeued from the active array and given
+ * the cpu. We should note that with the exception of interactive
+ * tasks, the expired queue will become the active queue after the active
+ * queue is empty, without explicitly dequeuing and requeuing tasks in the
+ * expired queue. (Interactive tasks may be requeued directly to the
+ * active queue, thus delaying tasks in the expired queue from running;
+ * see scheduler_tick()).
+ *
+ * This function is only called from sched_info_arrive(), rather than
+ * dequeue_task(). Even though a task may be queued and dequeued multiple
+ * times as it is shuffled about, we're really interested in knowing how
+ * long it was from the *first* time it was queued to the time that it
+ * finally hit a cpu.
+ */
+static inline void sched_info_dequeued(task_t *t)
{
- spin_unlock_irq(&rq->lock);
+ t->sched_info.last_queued = 0;
+}
+
+/*
+ * Called when a task finally hits the cpu. We can now calculate how
+ * long it was waiting to run. We also note when it began so that we
+ * can keep stats on how long its timeslice is.
+ */
+static void sched_info_arrive(task_t *t)
+{
+ unsigned long now = jiffies, diff = 0;
+ struct runqueue *rq = task_rq(t);
+
+ if (t->sched_info.last_queued)
+ diff = now - t->sched_info.last_queued;
+ sched_info_dequeued(t);
+ t->sched_info.run_delay += diff;
+ t->sched_info.last_arrival = now;
+ t->sched_info.pcnt++;
+
+ if (!rq)
+ return;
+
+ rq->rq_sched_info.run_delay += diff;
+ rq->rq_sched_info.pcnt++;
+}
+
+/*
+ * Called when a process is queued into either the active or expired
+ * array. The time is noted and later used to determine how long we
+ * had to wait for us to reach the cpu. Since the expired queue will
+ * become the active queue after active queue is empty, without dequeuing
+ * and requeuing any tasks, we are interested in queuing to either. It
+ * is unusual but not impossible for tasks to be dequeued and immediately
+ * requeued in the same or another array: this can happen in sched_yield(),
+ * set_user_nice(), and even load_balance() as it moves tasks from runqueue
+ * to runqueue.
+ *
+ * This function is only called from enqueue_task(), but also only updates
+ * the timestamp if it is already not set. It's assumed that
+ * sched_info_dequeued() will clear that stamp when appropriate.
+ */
+static inline void sched_info_queued(task_t *t)
+{
+ if (!t->sched_info.last_queued)
+ t->sched_info.last_queued = jiffies;
+}
+
+/*
+ * Called when a process ceases being the active-running process, either
+ * voluntarily or involuntarily. Now we can calculate how long we ran.
+ */
+static inline void sched_info_depart(task_t *t)
+{
+ struct runqueue *rq = task_rq(t);
+ unsigned long diff = jiffies - t->sched_info.last_arrival;
+
+ t->sched_info.cpu_time += diff;
+
+ if (rq)
+ rq->rq_sched_info.cpu_time += diff;
+}
+
+/*
+ * Called when tasks are switched involuntarily due, typically, to expiring
+ * their time slice. (This may also be called when switching to or from
+ * the idle task.) We are only called when prev != next.
+ */
+static inline void sched_info_switch(task_t *prev, task_t *next)
+{
+ struct runqueue *rq = task_rq(prev);
+
+ /*
+ * prev now departs the cpu. It's not interesting to record
+ * stats about how efficient we were at scheduling the idle
+ * process, however.
+ */
+ if (prev != rq->idle)
+ sched_info_depart(prev);
+
+ if (next != rq->idle)
+ sched_info_arrive(next);
}
+#else
+#define sched_info_queued(t) do { } while (0)
+#define sched_info_switch(t, next) do { } while (0)
+#endif /* CONFIG_SCHEDSTATS */
/*
* Adding/removing a task to/from a priority array:
*/
-static inline void dequeue_task(struct task_struct *p, prio_array_t *array)
+static void dequeue_task(struct task_struct *p, prio_array_t *array)
{
+ BUG_ON(p->state & TASK_ONHOLD);
array->nr_active--;
list_del(&p->run_list);
if (list_empty(array->queue + p->prio))
__clear_bit(p->prio, array->bitmap);
}
-static inline void enqueue_task(struct task_struct *p, prio_array_t *array)
+static void enqueue_task(struct task_struct *p, prio_array_t *array)
{
+ BUG_ON(p->state & TASK_ONHOLD);
+ sched_info_queued(p);
list_add_tail(&p->run_list, array->queue + p->prio);
__set_bit(p->prio, array->bitmap);
array->nr_active++;
p->array = array;
}
+/*
+ * Put task to the end of the run list without the overhead of dequeue
+ * followed by enqueue.
+ */
+static void requeue_task(struct task_struct *p, prio_array_t *array)
+{
+ BUG_ON(p->state & TASK_ONHOLD);
+ list_move_tail(&p->run_list, array->queue + p->prio);
+}
+
+static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
+{
+ BUG_ON(p->state & TASK_ONHOLD);
+ list_add(&p->run_list, array->queue + p->prio);
+ __set_bit(p->prio, array->bitmap);
+ array->nr_active++;
+ p->array = array;
+}
+
/*
* effective_prio - return the priority that is based on the static
* priority but is modified by bonuses/penalties.
static int effective_prio(task_t *p)
{
int bonus, prio;
+ struct vx_info *vxi;
if (rt_task(p))
return p->prio;
bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;
prio = p->static_prio - bonus;
+
+ if ((vxi = p->vx_info) &&
+ vx_info_flags(vxi, VXF_SCHED_PRIO, 0))
+ prio += vx_effective_vavavoom(vxi, MAX_USER_PRIO);
+
if (prio < MAX_RT_PRIO)
prio = MAX_RT_PRIO;
if (prio > MAX_PRIO-1)
/*
* __activate_task - move a task to the runqueue.
*/
-static inline void __activate_task(task_t *p, runqueue_t *rq)
+static void __activate_task(task_t *p, runqueue_t *rq)
+{
+ prio_array_t *target = rq->active;
+
+ if (batch_task(p))
+ target = rq->expired;
+ enqueue_task(p, target);
+ rq->nr_running++;
+}
+
+/*
+ * __activate_idle_task - move idle task to the _front_ of runqueue.
+ */
+static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
{
- enqueue_task(p, rq->active);
- nr_running_inc(rq);
+ enqueue_task_head(p, rq->active);
+ rq->nr_running++;
}
-static void recalc_task_prio(task_t *p, unsigned long long now)
+static int recalc_task_prio(task_t *p, unsigned long long now)
{
+ /* Caller must always ensure 'now >= p->timestamp' */
unsigned long long __sleep_time = now - p->timestamp;
unsigned long sleep_time;
- if (__sleep_time > NS_MAX_SLEEP_AVG)
- sleep_time = NS_MAX_SLEEP_AVG;
- else
- sleep_time = (unsigned long)__sleep_time;
+ if (batch_task(p))
+ sleep_time = 0;
+ else {
+ if (__sleep_time > NS_MAX_SLEEP_AVG)
+ sleep_time = NS_MAX_SLEEP_AVG;
+ else
+ sleep_time = (unsigned long)__sleep_time;
+ }
if (likely(sleep_time > 0)) {
/*
* User tasks that sleep a long time are categorised as
- * idle and will get just interactive status to stay active &
- * prevent them suddenly becoming cpu hogs and starving
- * other processes.
+ * idle. They will only have their sleep_avg increased to a
+ * level that makes them just interactive priority to stay
+ * active yet prevent them suddenly becoming cpu hogs and
+ * starving other processes.
*/
- if (p->mm && p->activated != -1 &&
- sleep_time > INTERACTIVE_SLEEP(p)) {
- p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
- AVG_TIMESLICE);
- if (!HIGH_CREDIT(p))
- p->interactive_credit++;
- } else {
- /*
- * The lower the sleep avg a task has the more
- * rapidly it will rise with sleep time.
- */
- sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1;
-
- /*
- * Tasks with low interactive_credit are limited to
- * one timeslice worth of sleep avg bonus.
- */
- if (LOW_CREDIT(p) &&
- sleep_time > JIFFIES_TO_NS(task_timeslice(p)))
- sleep_time = JIFFIES_TO_NS(task_timeslice(p));
+ if (p->mm && sleep_time > INTERACTIVE_SLEEP(p)) {
+ unsigned long ceiling;
+ ceiling = JIFFIES_TO_NS(MAX_SLEEP_AVG -
+ DEF_TIMESLICE);
+ if (p->sleep_avg < ceiling)
+ p->sleep_avg = ceiling;
+ } else {
/*
- * Non high_credit tasks waking from uninterruptible
- * sleep are limited in their sleep_avg rise as they
- * are likely to be cpu hogs waiting on I/O
+ * Tasks waking from uninterruptible sleep are
+ * limited in their sleep_avg rise as they
+ * are likely to be waiting on I/O
*/
- if (p->activated == -1 && !HIGH_CREDIT(p) && p->mm) {
+ if (p->sleep_type == SLEEP_NONINTERACTIVE && p->mm) {
if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
sleep_time = 0;
else if (p->sleep_avg + sleep_time >=
*/
p->sleep_avg += sleep_time;
- if (p->sleep_avg > NS_MAX_SLEEP_AVG) {
+ if (p->sleep_avg > NS_MAX_SLEEP_AVG)
p->sleep_avg = NS_MAX_SLEEP_AVG;
- if (!HIGH_CREDIT(p))
- p->interactive_credit++;
- }
}
}
- p->prio = effective_prio(p);
+ return effective_prio(p);
}
/*
* Update all the scheduling statistics stuff. (sleep average
* calculation, priority modifiers, etc.)
*/
-static inline void activate_task(task_t *p, runqueue_t *rq)
+static void activate_task(task_t *p, runqueue_t *rq, int local)
{
- unsigned long long now = sched_clock();
+ unsigned long long now;
- recalc_task_prio(p, now);
+ now = sched_clock();
+#ifdef CONFIG_SMP
+ if (!local) {
+ /* Compensate for drifting sched_clock */
+ runqueue_t *this_rq = this_rq();
+ now = (now - this_rq->timestamp_last_tick)
+ + rq->timestamp_last_tick;
+ }
+#endif
+
+ if (!rt_task(p))
+ p->prio = recalc_task_prio(p, now);
/*
* This checks to make sure it's not an uninterruptible task
* that is now waking up.
*/
- if (!p->activated) {
+ if (p->sleep_type == SLEEP_NORMAL) {
/*
* Tasks which were woken up by interrupts (ie. hw events)
* are most likely of interactive nature. So we give them
* on a CPU, first time around:
*/
if (in_interrupt())
- p->activated = 2;
+ p->sleep_type = SLEEP_INTERRUPTED;
else {
/*
* Normal first-time wakeups get a credit too for
* on-runqueue time, but it will be weighted down:
*/
- p->activated = 1;
+ p->sleep_type = SLEEP_INTERACTIVE;
}
}
p->timestamp = now;
+ vx_activate_task(p);
__activate_task(p, rq);
}
/*
* deactivate_task - remove a task from the runqueue.
*/
-static inline void deactivate_task(struct task_struct *p, runqueue_t *rq)
+static void __deactivate_task(struct task_struct *p, runqueue_t *rq)
{
- nr_running_dec(rq);
- if (p->state == TASK_UNINTERRUPTIBLE)
- rq->nr_uninterruptible++;
+ rq->nr_running--;
dequeue_task(p, p->array);
p->array = NULL;
}
+static inline
+void deactivate_task(struct task_struct *p, runqueue_t *rq)
+{
+ vx_deactivate_task(p);
+ __deactivate_task(p, rq);
+}
+
+
+#ifdef CONFIG_VSERVER_HARDCPU
+/*
+ * vx_hold_task - put a task on the hold queue
+ */
+static inline
+void vx_hold_task(struct vx_info *vxi,
+ struct task_struct *p, runqueue_t *rq)
+{
+ __deactivate_task(p, rq);
+ p->state |= TASK_ONHOLD;
+ /* a new one on hold */
+ vx_onhold_inc(vxi);
+ list_add_tail(&p->run_list, &rq->hold_queue);
+}
+
+/*
+ * vx_unhold_task - put a task back to the runqueue
+ */
+static inline
+void vx_unhold_task(struct vx_info *vxi,
+ struct task_struct *p, runqueue_t *rq)
+{
+ list_del(&p->run_list);
+ /* one less waiting */
+ vx_onhold_dec(vxi);
+ p->state &= ~TASK_ONHOLD;
+ enqueue_task(p, rq->expired);
+ rq->nr_running++;
+
+ if (p->static_prio < rq->best_expired_prio)
+ rq->best_expired_prio = p->static_prio;
+}
+#else
+static inline
+void vx_hold_task(struct vx_info *vxi,
+ struct task_struct *p, runqueue_t *rq)
+{
+ return;
+}
+
+static inline
+void vx_unhold_task(struct vx_info *vxi,
+ struct task_struct *p, runqueue_t *rq)
+{
+ return;
+}
+#endif /* CONFIG_VSERVER_HARDCPU */
+
+
/*
* resched_task - mark a task 'to be rescheduled now'.
*
* might also involve a cross-CPU call to trigger the scheduler on
* the target CPU.
*/
-static inline void resched_task(task_t *p)
-{
#ifdef CONFIG_SMP
- int need_resched, nrpolling;
+static void resched_task(task_t *p)
+{
+ int cpu;
- preempt_disable();
- /* minimise the chance of sending an interrupt to poll_idle() */
- nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
- need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
- nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
+ assert_spin_locked(&task_rq(p)->lock);
- if (!need_resched && !nrpolling && (task_cpu(p) != smp_processor_id()))
- smp_send_reschedule(task_cpu(p));
- preempt_enable();
+ if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+ return;
+
+ set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+
+ cpu = task_cpu(p);
+ if (cpu == smp_processor_id())
+ return;
+
+ /* NEED_RESCHED must be visible before we test POLLING_NRFLAG */
+ smp_mb();
+ if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG))
+ smp_send_reschedule(cpu);
+}
#else
+static inline void resched_task(task_t *p)
+{
+ assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
-#endif
}
+#endif
/**
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
*/
-inline int task_curr(task_t *p)
+inline int task_curr(const task_t *p)
{
return cpu_curr(task_cpu(p)) == p;
}
#ifdef CONFIG_SMP
typedef struct {
struct list_head list;
+
task_t *task;
+ int dest_cpu;
+
struct completion done;
} migration_req_t;
/*
- * The task's runqueue lock must be held, and the new mask must be valid.
+ * The task's runqueue lock must be held.
* Returns true if you have to wait for migration thread.
*/
-static int __set_cpus_allowed(task_t *p, cpumask_t new_mask,
- migration_req_t *req)
+static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
{
runqueue_t *rq = task_rq(p);
- p->cpus_allowed = new_mask;
- /*
- * Can the task run on the task's current CPU? If not then
- * migrate the thread off to a proper CPU.
- */
- if (cpu_isset(task_cpu(p), new_mask))
- return 0;
-
/*
* If the task is not on a runqueue (and not running), then
* it is sufficient to simply update the task's cpu field.
*/
if (!p->array && !task_running(rq, p)) {
- set_task_cpu(p, any_online_cpu(p->cpus_allowed));
+ set_task_cpu(p, dest_cpu);
return 0;
}
init_completion(&req->done);
req->task = p;
+ req->dest_cpu = dest_cpu;
list_add(&req->list, &rq->migration_queue);
return 1;
}
* smp_call_function() if an IPI is sent by the same process we are
* waiting to become inactive.
*/
-void wait_task_inactive(task_t * p)
+void wait_task_inactive(task_t *p)
{
unsigned long flags;
runqueue_t *rq;
repeat:
rq = task_rq_lock(p, &flags);
/* Must be off runqueue entirely, not preempted. */
- if (unlikely(p->array)) {
+ if (unlikely(p->array || task_running(rq, p))) {
/* If it's preempted, we yield. It could be a while. */
preempted = !task_running(rq, p);
task_rq_unlock(rq, &flags);
*
* Cause a process which is running on another CPU to enter
* kernel-mode, without any delay. (to get signals handled.)
+ *
+ * NOTE: this function doesnt have to take the runqueue lock,
+ * because all it wants to ensure is that the remote task enters
+ * the kernel. If the IPI races and the task has been migrated
+ * to another CPU then no harm is done and the purpose has been
+ * achieved as well.
*/
void kick_process(task_t *p)
{
preempt_enable();
}
-EXPORT_SYMBOL_GPL(kick_process);
-
-#endif
-
-/***
- * try_to_wake_up - wake up a thread
- * @p: the to-be-woken-up thread
- * @state: the mask of task states that can be woken
- * @sync: do a synchronous wakeup?
- *
- * Put it on the run-queue if it's not already there. The "current"
- * thread is always on the run-queue (except when the actual
- * re-schedule is in progress), and as such you're allowed to do
- * the simpler "current->state = TASK_RUNNING" to mark yourself
- * runnable without the overhead of this.
+/*
+ * Return a low guess at the load of a migration-source cpu.
*
- * returns failure only if the task is already active.
+ * We want to under-estimate the load of migration sources, to
+ * balance conservatively.
*/
-static int try_to_wake_up(task_t * p, unsigned int state, int sync)
+static inline unsigned long source_load(int cpu, int type)
{
- unsigned long flags;
- int success = 0;
- long old_state;
+ runqueue_t *rq = cpu_rq(cpu);
+ unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+ if (type == 0)
+ return load_now;
+
+ return min(rq->cpu_load[type-1], load_now);
+}
+
+/*
+ * Return a high guess at the load of a migration-target cpu
+ */
+static inline unsigned long target_load(int cpu, int type)
+{
+ runqueue_t *rq = cpu_rq(cpu);
+ unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+ if (type == 0)
+ return load_now;
+
+ return max(rq->cpu_load[type-1], load_now);
+}
+
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+{
+ struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+ unsigned long min_load = ULONG_MAX, this_load = 0;
+ int load_idx = sd->forkexec_idx;
+ int imbalance = 100 + (sd->imbalance_pct-100)/2;
+
+ do {
+ unsigned long load, avg_load;
+ int local_group;
+ int i;
+
+ /* Skip over this group if it has no CPUs allowed */
+ if (!cpus_intersects(group->cpumask, p->cpus_allowed))
+ goto nextgroup;
+
+ local_group = cpu_isset(this_cpu, group->cpumask);
+
+ /* Tally up the load of all CPUs in the group */
+ avg_load = 0;
+
+ for_each_cpu_mask(i, group->cpumask) {
+ /* Bias balancing toward cpus of our domain */
+ if (local_group)
+ load = source_load(i, load_idx);
+ else
+ load = target_load(i, load_idx);
+
+ avg_load += load;
+ }
+
+ /* Adjust by relative CPU power of the group */
+ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+ if (local_group) {
+ this_load = avg_load;
+ this = group;
+ } else if (avg_load < min_load) {
+ min_load = avg_load;
+ idlest = group;
+ }
+nextgroup:
+ group = group->next;
+ } while (group != sd->groups);
+
+ if (!idlest || 100*this_load < imbalance*min_load)
+ return NULL;
+ return idlest;
+}
+
+/*
+ * find_idlest_queue - find the idlest runqueue among the cpus in group.
+ */
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+ cpumask_t tmp;
+ unsigned long load, min_load = ULONG_MAX;
+ int idlest = -1;
+ int i;
+
+ /* Traverse only the allowed CPUs */
+ cpus_and(tmp, group->cpumask, p->cpus_allowed);
+
+ for_each_cpu_mask(i, tmp) {
+ load = source_load(i, 0);
+
+ if (load < min_load || (load == min_load && i == this_cpu)) {
+ min_load = load;
+ idlest = i;
+ }
+ }
+
+ return idlest;
+}
+
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int sched_balance_self(int cpu, int flag)
+{
+ struct task_struct *t = current;
+ struct sched_domain *tmp, *sd = NULL;
+
+ for_each_domain(cpu, tmp)
+ if (tmp->flags & flag)
+ sd = tmp;
+
+ while (sd) {
+ cpumask_t span;
+ struct sched_group *group;
+ int new_cpu;
+ int weight;
+
+ span = sd->span;
+ group = find_idlest_group(sd, t, cpu);
+ if (!group)
+ goto nextlevel;
+
+ new_cpu = find_idlest_cpu(group, t, cpu);
+ if (new_cpu == -1 || new_cpu == cpu)
+ goto nextlevel;
+
+ /* Now try balancing at a lower domain level */
+ cpu = new_cpu;
+nextlevel:
+ sd = NULL;
+ weight = cpus_weight(span);
+ for_each_domain(cpu, tmp) {
+ if (weight <= cpus_weight(tmp->span))
+ break;
+ if (tmp->flags & flag)
+ sd = tmp;
+ }
+ /* while loop will break here if sd == NULL */
+ }
+
+ return cpu;
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * not idle and an idle cpu is available. The span of cpus to
+ * search starts with cpus closest then further out as needed,
+ * so we always favor a closer, idle cpu.
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, task_t *p)
+{
+ cpumask_t tmp;
+ struct sched_domain *sd;
+ int i;
+
+ if (idle_cpu(cpu))
+ return cpu;
+
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_IDLE) {
+ cpus_and(tmp, sd->span, p->cpus_allowed);
+ for_each_cpu_mask(i, tmp) {
+ if (idle_cpu(i))
+ return i;
+ }
+ }
+ else
+ break;
+ }
+ return cpu;
+}
+#else
+static inline int wake_idle(int cpu, task_t *p)
+{
+ return cpu;
+}
+#endif
+
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @sync: do a synchronous wakeup?
+ *
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * returns failure only if the task is already active.
+ */
+static int try_to_wake_up(task_t *p, unsigned int state, int sync)
+{
+ int cpu, this_cpu, success = 0;
+ unsigned long flags;
+ long old_state;
runqueue_t *rq;
+#ifdef CONFIG_SMP
+ unsigned long load, this_load;
+ struct sched_domain *sd, *this_sd = NULL;
+ int new_cpu;
+#endif
-repeat_lock_task:
rq = task_rq_lock(p, &flags);
old_state = p->state;
- if (old_state & state) {
- if (!p->array) {
+
+ /* we need to unhold suspended tasks */
+ if (old_state & TASK_ONHOLD) {
+ vx_unhold_task(p->vx_info, p, rq);
+ old_state = p->state;
+ }
+ if (!(old_state & state))
+ goto out;
+
+ if (p->array)
+ goto out_running;
+
+ cpu = task_cpu(p);
+ this_cpu = smp_processor_id();
+
+#ifdef CONFIG_SMP
+ if (unlikely(task_running(rq, p)))
+ goto out_activate;
+
+ new_cpu = cpu;
+
+ schedstat_inc(rq, ttwu_cnt);
+ if (cpu == this_cpu) {
+ schedstat_inc(rq, ttwu_local);
+ goto out_set_cpu;
+ }
+
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(cpu, sd->span)) {
+ schedstat_inc(sd, ttwu_wake_remote);
+ this_sd = sd;
+ break;
+ }
+ }
+
+ if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+ goto out_set_cpu;
+
+ /*
+ * Check for affine wakeup and passive balancing possibilities.
+ */
+ if (this_sd) {
+ int idx = this_sd->wake_idx;
+ unsigned int imbalance;
+
+ imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+ load = source_load(cpu, idx);
+ this_load = target_load(this_cpu, idx);
+
+ new_cpu = this_cpu; /* Wake to this CPU if we can */
+
+ if (this_sd->flags & SD_WAKE_AFFINE) {
+ unsigned long tl = this_load;
/*
- * Fast-migrate the task if it's not running or runnable
- * currently. Do not violate hard affinity.
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
*/
- if (unlikely(sync && !task_running(rq, p) &&
- (task_cpu(p) != smp_processor_id()) &&
- cpu_isset(smp_processor_id(),
- p->cpus_allowed) &&
- !cpu_is_offline(smp_processor_id()))) {
- set_task_cpu(p, smp_processor_id());
- task_rq_unlock(rq, &flags);
- goto repeat_lock_task;
- }
- if (old_state == TASK_UNINTERRUPTIBLE) {
- rq->nr_uninterruptible--;
+ if (sync)
+ tl -= SCHED_LOAD_SCALE;
+
+ if ((tl <= load &&
+ tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) ||
+ 100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) {
/*
- * Tasks on involuntary sleep don't earn
- * sleep_avg beyond just interactive state.
+ * This domain has SD_WAKE_AFFINE and
+ * p is cache cold in this domain, and
+ * there is no bad imbalance.
*/
- p->activated = -1;
+ schedstat_inc(this_sd, ttwu_move_affine);
+ goto out_set_cpu;
}
- if (sync && (task_cpu(p) == smp_processor_id()))
- __activate_task(p, rq);
- else {
- activate_task(p, rq);
- if (TASK_PREEMPTS_CURR(p, rq))
- resched_task(rq->curr);
+ }
+
+ /*
+ * Start passive balancing when half the imbalance_pct
+ * limit is reached.
+ */
+ if (this_sd->flags & SD_WAKE_BALANCE) {
+ if (imbalance*this_load <= 100*load) {
+ schedstat_inc(this_sd, ttwu_move_balance);
+ goto out_set_cpu;
}
- success = 1;
}
- p->state = TASK_RUNNING;
}
+
+ new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
+out_set_cpu:
+ new_cpu = wake_idle(new_cpu, p);
+ if (new_cpu != cpu) {
+ set_task_cpu(p, new_cpu);
+ task_rq_unlock(rq, &flags);
+ /* might preempt at this point */
+ rq = task_rq_lock(p, &flags);
+ old_state = p->state;
+ if (!(old_state & state))
+ goto out;
+ if (p->array)
+ goto out_running;
+
+ this_cpu = smp_processor_id();
+ cpu = task_cpu(p);
+ }
+
+out_activate:
+#endif /* CONFIG_SMP */
+ if (old_state == TASK_UNINTERRUPTIBLE) {
+ rq->nr_uninterruptible--;
+ vx_uninterruptible_dec(p);
+ /*
+ * Tasks on involuntary sleep don't earn
+ * sleep_avg beyond just interactive state.
+ */
+ p->sleep_type = SLEEP_NONINTERACTIVE;
+ } else
+
+ /*
+ * Tasks that have marked their sleep as noninteractive get
+ * woken up with their sleep average not weighted in an
+ * interactive way.
+ */
+ if (old_state & TASK_NONINTERACTIVE)
+ p->sleep_type = SLEEP_NONINTERACTIVE;
+
+
+ activate_task(p, rq, cpu == this_cpu);
+ /*
+ * Sync wakeups (i.e. those types of wakeups where the waker
+ * has indicated that it will leave the CPU in short order)
+ * don't trigger a preemption, if the woken up task will run on
+ * this cpu. (in this case the 'I will reschedule' promise of
+ * the waker guarantees that the freshly woken up task is going
+ * to be considered on this CPU.)
+ */
+ if (!sync || cpu != this_cpu) {
+ if (TASK_PREEMPTS_CURR(p, rq))
+ resched_task(rq->curr);
+ }
+ success = 1;
+
+out_running:
+ p->state = TASK_RUNNING;
+out:
task_rq_unlock(rq, &flags);
return success;
}
-int fastcall wake_up_process(task_t * p)
+
+int fastcall wake_up_process(task_t *p)
{
- return try_to_wake_up(p, TASK_STOPPED |
- TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
+ return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
+ TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}
EXPORT_SYMBOL(wake_up_process);
* Perform scheduler related setup for a newly forked process p.
* p is forked by current.
*/
-void fastcall sched_fork(task_t *p)
+void fastcall sched_fork(task_t *p, int clone_flags)
{
+ int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+ cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
+#endif
+ set_task_cpu(p, cpu);
+
/*
* We mark the process as running here, but have not actually
* inserted it onto the runqueue yet. This guarantees that
p->state = TASK_RUNNING;
INIT_LIST_HEAD(&p->run_list);
p->array = NULL;
- spin_lock_init(&p->switch_lock);
+#ifdef CONFIG_SCHEDSTATS
+ memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ p->oncpu = 0;
+#endif
#ifdef CONFIG_PREEMPT
- /*
- * During context-switch we hold precisely one spinlock, which
- * schedule_tail drops. (in the common case it's this_rq()->lock,
- * but it also can be p->switch_lock.) So we compensate with a count
- * of 1. Also, we want to start with kernel preemption disabled.
- */
- p->thread_info->preempt_count = 1;
+ /* Want to start with kernel preemption disabled. */
+ task_thread_info(p)->preempt_count = 1;
#endif
/*
* Share the timeslice between parent and child, thus the
p->first_time_slice = 1;
current->time_slice >>= 1;
p->timestamp = sched_clock();
- if (!current->time_slice) {
+ if (unlikely(!current->time_slice)) {
/*
- * This case is rare, it happens when the parent has only
- * a single jiffy left from its timeslice. Taking the
+ * This case is rare, it happens when the parent has only
+ * a single jiffy left from its timeslice. Taking the
* runqueue lock is not a problem.
*/
current->time_slice = 1;
- preempt_disable();
- scheduler_tick(0, 0);
- local_irq_enable();
- preempt_enable();
- } else
- local_irq_enable();
+ scheduler_tick();
+ }
+ local_irq_enable();
+ put_cpu();
}
/*
- * wake_up_forked_process - wake up a freshly forked process.
+ * wake_up_new_task - wake up a newly created task for the first time.
*
* This function will do some initial scheduler statistics housekeeping
- * that must be done for every newly created process.
+ * that must be done for every newly created context, then puts the task
+ * on the runqueue and wakes it.
*/
-void fastcall wake_up_forked_process(task_t * p)
+void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
{
unsigned long flags;
- runqueue_t *rq = task_rq_lock(current, &flags);
+ int this_cpu, cpu;
+ runqueue_t *rq, *this_rq;
+ rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
+ this_cpu = smp_processor_id();
+ cpu = task_cpu(p);
/*
* We decrease the sleep average of forking parents
* and children as well, to keep max-interactive tasks
- * from forking tasks that are max-interactive.
+ * from forking tasks that are max-interactive. The parent
+ * (current) is done further down, under its lock.
*/
- current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
- PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
-
p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
- p->interactive_credit = 0;
-
p->prio = effective_prio(p);
- set_task_cpu(p, smp_processor_id());
- if (unlikely(!current->array))
+ vx_activate_task(p);
+ if (likely(cpu == this_cpu)) {
+ if (!(clone_flags & CLONE_VM)) {
+ /*
+ * The VM isn't cloned, so we're in a good position to
+ * do child-runs-first in anticipation of an exec. This
+ * usually avoids a lot of COW overhead.
+ */
+ if (unlikely(!current->array))
+ __activate_task(p, rq);
+ else {
+ p->prio = current->prio;
+ BUG_ON(p->state & TASK_ONHOLD);
+ list_add_tail(&p->run_list, ¤t->run_list);
+ p->array = current->array;
+ p->array->nr_active++;
+ rq->nr_running++;
+ }
+ set_need_resched();
+ } else
+ /* Run child last */
+ __activate_task(p, rq);
+ /*
+ * We skip the following code due to cpu == this_cpu
+ *
+ * task_rq_unlock(rq, &flags);
+ * this_rq = task_rq_lock(current, &flags);
+ */
+ this_rq = rq;
+ } else {
+ this_rq = cpu_rq(this_cpu);
+
+ /*
+ * Not the local CPU - must adjust timestamp. This should
+ * get optimised away in the !CONFIG_SMP case.
+ */
+ p->timestamp = (p->timestamp - this_rq->timestamp_last_tick)
+ + rq->timestamp_last_tick;
__activate_task(p, rq);
- else {
- p->prio = current->prio;
- list_add_tail(&p->run_list, ¤t->run_list);
- p->array = current->array;
- p->array->nr_active++;
- nr_running_inc(rq);
+ if (TASK_PREEMPTS_CURR(p, rq))
+ resched_task(rq->curr);
+
+ /*
+ * Parent and child are on different CPUs, now get the
+ * parent runqueue to update the parent's ->sleep_avg:
+ */
+ task_rq_unlock(rq, &flags);
+ this_rq = task_rq_lock(current, &flags);
}
- task_rq_unlock(rq, &flags);
+ current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
+ PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
+ task_rq_unlock(this_rq, &flags);
}
/*
* artificially, because any timeslice recovered here
* was given away by the parent in the first place.)
*/
-void fastcall sched_exit(task_t * p)
+void fastcall sched_exit(task_t *p)
{
unsigned long flags;
runqueue_t *rq;
- local_irq_save(flags);
- if (p->first_time_slice) {
- p->parent->time_slice += p->time_slice;
- if (unlikely(p->parent->time_slice > MAX_TIMESLICE))
- p->parent->time_slice = MAX_TIMESLICE;
- }
- local_irq_restore(flags);
/*
* If the child was a (relative-) CPU hog then decrease
* the sleep_avg of the parent as well.
*/
rq = task_rq_lock(p->parent, &flags);
+ if (p->first_time_slice && task_cpu(p) == task_cpu(p->parent)) {
+ p->parent->time_slice += p->time_slice;
+ if (unlikely(p->parent->time_slice > task_timeslice(p)))
+ p->parent->time_slice = task_timeslice(p);
+ }
if (p->sleep_avg < p->parent->sleep_avg)
p->parent->sleep_avg = p->parent->sleep_avg /
(EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
task_rq_unlock(rq, &flags);
}
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void prepare_task_switch(runqueue_t *rq, task_t *next)
+{
+ prepare_lock_switch(rq, next);
+ prepare_arch_switch(next);
+}
+
/**
* finish_task_switch - clean up after a task-switch
+ * @rq: runqueue associated with task-switch
* @prev: the thread we just switched away from.
*
- * We enter this with the runqueue still locked, and finish_arch_switch()
- * will unlock it along with doing any other architecture-specific cleanup
- * actions.
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
*
* Note that we may have delayed dropping an mm in context_switch(). If
* so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
-static inline void finish_task_switch(task_t *prev)
+static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
+ __releases(rq->lock)
{
- runqueue_t *rq = this_rq();
struct mm_struct *mm = rq->prev_mm;
unsigned long prev_task_flags;
/*
* A task struct has one reference for the use as "current".
- * If a task dies, then it sets TASK_ZOMBIE in tsk->state and calls
- * schedule one last time. The schedule call will never return,
+ * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
+ * calls schedule one last time. The schedule call will never return,
* and the scheduled task must drop that reference.
- * The test for TASK_ZOMBIE must occur while the runqueue locks are
+ * The test for EXIT_ZOMBIE must occur while the runqueue locks are
* still held, otherwise prev could be scheduled on another cpu, die
* there before we look at prev->state, and then the reference would
* be dropped twice.
- * Manfred Spraul <manfred@colorfullife.com>
+ * Manfred Spraul <manfred@colorfullife.com>
*/
prev_task_flags = prev->flags;
- finish_arch_switch(rq, prev);
+ finish_arch_switch(prev);
+ finish_lock_switch(rq, prev);
if (mm)
mmdrop(mm);
- if (unlikely(prev_task_flags & PF_DEAD))
+ if (unlikely(prev_task_flags & PF_DEAD)) {
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
put_task_struct(prev);
+ }
}
/**
* @prev: the thread we just switched away from.
*/
asmlinkage void schedule_tail(task_t *prev)
+ __releases(rq->lock)
{
- finish_task_switch(prev);
-
+ runqueue_t *rq = this_rq();
+ finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+ /* In this case, finish_task_switch does not reenable preemption */
+ preempt_enable();
+#endif
if (current->set_child_tid)
put_user(current->pid, current->set_child_tid);
}
{
unsigned long i, sum = 0;
- for (i = 0; i < NR_CPUS; i++)
+ for_each_online_cpu(i)
sum += cpu_rq(i)->nr_running;
return sum;
{
unsigned long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_uninterruptible;
+ /*
+ * Since we read the counters lockless, it might be slightly
+ * inaccurate. Do not allow it to go below zero though:
+ */
+ if (unlikely((long)sum < 0))
+ sum = 0;
+
return sum;
}
{
unsigned long long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_switches;
return sum;
{
unsigned long i, sum = 0;
- for_each_cpu(i)
+ for_each_possible_cpu(i)
sum += atomic_read(&cpu_rq(i)->nr_iowait);
return sum;
}
+unsigned long nr_active(void)
+{
+ unsigned long i, running = 0, uninterruptible = 0;
+
+ for_each_online_cpu(i) {
+ running += cpu_rq(i)->nr_running;
+ uninterruptible += cpu_rq(i)->nr_uninterruptible;
+ }
+
+ if (unlikely((long)uninterruptible < 0))
+ uninterruptible = 0;
+
+ return running + uninterruptible;
+}
+
+#ifdef CONFIG_SMP
+
/*
* double_rq_lock - safely lock two runqueues
*
+ * We must take them in cpu order to match code in
+ * dependent_sleeper and wake_dependent_sleeper.
+ *
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
-static inline void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
+static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
+ __acquires(rq1->lock)
+ __acquires(rq2->lock)
{
- if (rq1 == rq2)
+ if (rq1 == rq2) {
spin_lock(&rq1->lock);
- else {
- if (rq1 < rq2) {
+ __acquire(rq2->lock); /* Fake it out ;) */
+ } else {
+ if (rq1->cpu < rq2->cpu) {
spin_lock(&rq1->lock);
spin_lock(&rq2->lock);
} else {
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
-static inline void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2)
+static void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2)
+ __releases(rq1->lock)
+ __releases(rq2->lock)
{
spin_unlock(&rq1->lock);
if (rq1 != rq2)
spin_unlock(&rq2->lock);
+ else
+ __release(rq2->lock);
+}
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+{
+ if (unlikely(!spin_trylock(&busiest->lock))) {
+ if (busiest->cpu < this_rq->cpu) {
+ spin_unlock(&this_rq->lock);
+ spin_lock(&busiest->lock);
+ spin_lock(&this_rq->lock);
+ } else
+ spin_lock(&busiest->lock);
+ }
}
-#ifdef CONFIG_NUMA
/*
* If dest_cpu is allowed for this process, migrate the task to it.
* This is accomplished by forcing the cpu_allowed mask to only
*/
static void sched_migrate_task(task_t *p, int dest_cpu)
{
- runqueue_t *rq;
migration_req_t req;
+ runqueue_t *rq;
unsigned long flags;
- cpumask_t old_mask, new_mask = cpumask_of_cpu(dest_cpu);
- lock_cpu_hotplug();
rq = task_rq_lock(p, &flags);
- old_mask = p->cpus_allowed;
- if (!cpu_isset(dest_cpu, old_mask) || !cpu_online(dest_cpu))
+ if (!cpu_isset(dest_cpu, p->cpus_allowed)
+ || unlikely(cpu_is_offline(dest_cpu)))
goto out;
/* force the process onto the specified CPU */
- if (__set_cpus_allowed(p, new_mask, &req)) {
- /* Need to wait for migration thread. */
+ if (migrate_task(p, dest_cpu, &req)) {
+ /* Need to wait for migration thread (might exit: take ref). */
+ struct task_struct *mt = rq->migration_thread;
+ get_task_struct(mt);
task_rq_unlock(rq, &flags);
- wake_up_process(rq->migration_thread);
+ wake_up_process(mt);
+ put_task_struct(mt);
wait_for_completion(&req.done);
-
- /* If we raced with sys_sched_setaffinity, don't
- * restore mask. */
- rq = task_rq_lock(p, &flags);
- if (likely(cpus_equal(p->cpus_allowed, new_mask))) {
- /* Restore old mask: won't need migration
- * thread, since current cpu is allowed. */
- BUG_ON(__set_cpus_allowed(p, old_mask, NULL));
- }
+ return;
}
out:
task_rq_unlock(rq, &flags);
- unlock_cpu_hotplug();
}
/*
- * Find the least loaded CPU. Slightly favor the current CPU by
- * setting its runqueue length as the minimum to start.
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
*/
-static int sched_best_cpu(struct task_struct *p)
+void sched_exec(void)
{
- int i, minload, load, best_cpu, node = 0;
- cpumask_t cpumask;
-
- best_cpu = task_cpu(p);
- if (cpu_rq(best_cpu)->nr_running <= 2)
- return best_cpu;
-
- minload = 10000000;
- for_each_node_with_cpus(i) {
- /*
- * Node load is always divided by nr_cpus_node to normalise
- * load values in case cpu count differs from node to node.
- * We first multiply node_nr_running by 10 to get a little
- * better resolution.
- */
- load = 10 * atomic_read(&node_nr_running[i]) / nr_cpus_node(i);
- if (load < minload) {
- minload = load;
- node = i;
- }
- }
-
- minload = 10000000;
- cpumask = node_to_cpumask(node);
- for (i = 0; i < NR_CPUS; ++i) {
- if (!cpu_isset(i, cpumask))
- continue;
- if (cpu_rq(i)->nr_running < minload) {
- best_cpu = i;
- minload = cpu_rq(i)->nr_running;
- }
- }
- return best_cpu;
+ int new_cpu, this_cpu = get_cpu();
+ new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
+ put_cpu();
+ if (new_cpu != this_cpu)
+ sched_migrate_task(current, new_cpu);
}
-void sched_balance_exec(void)
-{
- int new_cpu;
-
- if (numnodes > 1) {
- new_cpu = sched_best_cpu(current);
- if (new_cpu != smp_processor_id())
- sched_migrate_task(current, new_cpu);
- }
-}
-
-/*
- * Find the busiest node. All previous node loads contribute with a
- * geometrically deccaying weight to the load measure:
- * load_{t} = load_{t-1}/2 + nr_node_running_{t}
- * This way sudden load peaks are flattened out a bit.
- * Node load is divided by nr_cpus_node() in order to compare nodes
- * of different cpu count but also [first] multiplied by 10 to
- * provide better resolution.
- */
-static int find_busiest_node(int this_node)
-{
- int i, node = -1, load, this_load, maxload;
-
- if (!nr_cpus_node(this_node))
- return node;
- this_load = maxload = (this_rq()->prev_node_load[this_node] >> 1)
- + (10 * atomic_read(&node_nr_running[this_node])
- / nr_cpus_node(this_node));
- this_rq()->prev_node_load[this_node] = this_load;
- for_each_node_with_cpus(i) {
- if (i == this_node)
- continue;
- load = (this_rq()->prev_node_load[i] >> 1)
- + (10 * atomic_read(&node_nr_running[i])
- / nr_cpus_node(i));
- this_rq()->prev_node_load[i] = load;
- if (load > maxload && (100*load > NODE_THRESHOLD*this_load)) {
- maxload = load;
- node = i;
- }
- }
- return node;
-}
-
-#endif /* CONFIG_NUMA */
-
-#ifdef CONFIG_SMP
-
-/*
- * double_lock_balance - lock the busiest runqueue
- *
- * this_rq is locked already. Recalculate nr_running if we have to
- * drop the runqueue lock.
- */
-static inline
-unsigned int double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest,
- int this_cpu, int idle,
- unsigned int nr_running)
-{
- if (unlikely(!spin_trylock(&busiest->lock))) {
- if (busiest < this_rq) {
- spin_unlock(&this_rq->lock);
- spin_lock(&busiest->lock);
- spin_lock(&this_rq->lock);
- /* Need to recalculate nr_running */
- if (idle || (this_rq->nr_running >
- this_rq->prev_cpu_load[this_cpu]))
- nr_running = this_rq->nr_running;
- else
- nr_running = this_rq->prev_cpu_load[this_cpu];
- } else
- spin_lock(&busiest->lock);
- }
- return nr_running;
-}
-
-/*
- * find_busiest_queue - find the busiest runqueue among the cpus in cpumask.
- */
-static inline
-runqueue_t *find_busiest_queue(runqueue_t *this_rq, int this_cpu, int idle,
- int *imbalance, cpumask_t cpumask)
-{
- int nr_running, load, max_load, i;
- runqueue_t *busiest, *rq_src;
-
- /*
- * We search all runqueues to find the most busy one.
- * We do this lockless to reduce cache-bouncing overhead,
- * we re-check the 'best' source CPU later on again, with
- * the lock held.
- *
- * We fend off statistical fluctuations in runqueue lengths by
- * saving the runqueue length (as seen by the balancing CPU) during
- * the previous load-balancing operation and using the smaller one
- * of the current and saved lengths. If a runqueue is long enough
- * for a longer amount of time then we recognize it and pull tasks
- * from it.
- *
- * The 'current runqueue length' is a statistical maximum variable,
- * for that one we take the longer one - to avoid fluctuations in
- * the other direction. So for a load-balance to happen it needs
- * stable long runqueue on the target CPU and stable short runqueue
- * on the local runqueue.
- *
- * We make an exception if this CPU is about to become idle - in
- * that case we are less picky about moving a task across CPUs and
- * take what can be taken.
- */
- if (idle || (this_rq->nr_running > this_rq->prev_cpu_load[this_cpu]))
- nr_running = this_rq->nr_running;
- else
- nr_running = this_rq->prev_cpu_load[this_cpu];
-
- busiest = NULL;
- max_load = 1;
- for (i = 0; i < NR_CPUS; i++) {
- if (!cpu_isset(i, cpumask))
- continue;
-
- rq_src = cpu_rq(i);
- if (idle || (rq_src->nr_running < this_rq->prev_cpu_load[i]))
- load = rq_src->nr_running;
- else
- load = this_rq->prev_cpu_load[i];
- this_rq->prev_cpu_load[i] = rq_src->nr_running;
-
- if ((load > max_load) && (rq_src != this_rq)) {
- busiest = rq_src;
- max_load = load;
- }
- }
-
- if (likely(!busiest))
- goto out;
-
- *imbalance = max_load - nr_running;
-
- /* It needs an at least ~25% imbalance to trigger balancing. */
- if (!idle && ((*imbalance)*4 < max_load)) {
- busiest = NULL;
- goto out;
- }
-
- nr_running = double_lock_balance(this_rq, busiest, this_cpu,
- idle, nr_running);
- /*
- * Make sure nothing changed since we checked the
- * runqueue length.
- */
- if (busiest->nr_running <= nr_running) {
- spin_unlock(&busiest->lock);
- busiest = NULL;
- }
-out:
- return busiest;
-}
-
-/*
- * pull_task - move a task from a remote runqueue to the local runqueue.
- * Both runqueues must be locked.
- */
-static inline
-void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
- runqueue_t *this_rq, int this_cpu)
+/*
+ * pull_task - move a task from a remote runqueue to the local runqueue.
+ * Both runqueues must be locked.
+ */
+static
+void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
+ runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
{
dequeue_task(p, src_array);
- nr_running_dec(src_rq);
+ src_rq->nr_running--;
set_task_cpu(p, this_cpu);
- nr_running_inc(this_rq);
- enqueue_task(p, this_rq->active);
- p->timestamp = sched_clock() -
- (src_rq->timestamp_last_tick - p->timestamp);
+ this_rq->nr_running++;
+ enqueue_task(p, this_array);
+ p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
+ + this_rq->timestamp_last_tick;
/*
* Note that idle threads have a prio of MAX_PRIO, for this test
* to be always true for them.
*/
if (TASK_PREEMPTS_CURR(p, this_rq))
- set_need_resched();
+ resched_task(this_rq->curr);
}
/*
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
-static inline
-int can_migrate_task(task_t *tsk, runqueue_t *rq, int this_cpu, int idle)
+static
+int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
+ struct sched_domain *sd, enum idle_type idle,
+ int *all_pinned)
{
- unsigned long delta = rq->timestamp_last_tick - tsk->timestamp;
-
/*
* We do not migrate tasks that are:
* 1) running (obviously), or
* 2) cannot be migrated to this CPU due to cpus_allowed, or
* 3) are cache-hot on their current CPU.
*/
- if (task_running(rq, tsk))
+ if (!cpu_isset(this_cpu, p->cpus_allowed))
return 0;
- if (!cpu_isset(this_cpu, tsk->cpus_allowed))
+ *all_pinned = 0;
+
+ if (task_running(rq, p))
return 0;
- if (!idle && (delta <= JIFFIES_TO_NS(cache_decay_ticks)))
+
+ /*
+ * Aggressive migration if:
+ * 1) task is cache cold, or
+ * 2) too many balance attempts have failed.
+ */
+
+ if (sd->nr_balance_failed > sd->cache_nice_tries)
+ return 1;
+
+ if (task_hot(p, rq->timestamp_last_tick, sd))
return 0;
return 1;
}
/*
- * Current runqueue is empty, or rebalance tick: if there is an
- * inbalance (current runqueue is too short) then pull from
- * busiest runqueue(s).
+ * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq,
+ * as part of a balancing operation within "domain". Returns the number of
+ * tasks moved.
*
- * We call this with the current runqueue locked,
- * irqs disabled.
+ * Called with both runqueues locked.
*/
-static void load_balance(runqueue_t *this_rq, int idle, cpumask_t cpumask)
+static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
+ unsigned long max_nr_move, struct sched_domain *sd,
+ enum idle_type idle, int *all_pinned)
{
- int imbalance, idx, this_cpu = smp_processor_id();
- runqueue_t *busiest;
- prio_array_t *array;
+ prio_array_t *array, *dst_array;
struct list_head *head, *curr;
+ int idx, pulled = 0, pinned = 0;
task_t *tmp;
- if (cpu_is_offline(this_cpu))
- goto out;
-
- busiest = find_busiest_queue(this_rq, this_cpu, idle,
- &imbalance, cpumask);
- if (!busiest)
+ if (max_nr_move == 0)
goto out;
- /*
- * We only want to steal a number of tasks equal to 1/2 the imbalance,
- * otherwise we'll just shift the imbalance to the new queue:
- */
- imbalance /= 2;
+ pinned = 1;
/*
* We first consider expired tasks. Those will likely not be
* be cache-cold, thus switching CPUs has the least effect
* on them.
*/
- if (busiest->expired->nr_active)
+ if (busiest->expired->nr_active) {
array = busiest->expired;
- else
+ dst_array = this_rq->expired;
+ } else {
array = busiest->active;
+ dst_array = this_rq->active;
+ }
new_array:
/* Start searching at priority 0: */
else
idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
if (idx >= MAX_PRIO) {
- if (array == busiest->expired) {
+ if (array == busiest->expired && busiest->active->nr_active) {
array = busiest->active;
+ dst_array = this_rq->active;
goto new_array;
}
- goto out_unlock;
+ goto out;
}
head = array->queue + idx;
curr = curr->prev;
- if (!can_migrate_task(tmp, busiest, this_cpu, idle)) {
+ if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
if (curr != head)
goto skip_queue;
idx++;
goto skip_bitmap;
}
- pull_task(busiest, array, tmp, this_rq, this_cpu);
- /* Only migrate one task if we are idle */
- if (!idle && --imbalance) {
+#ifdef CONFIG_SCHEDSTATS
+ if (task_hot(tmp, busiest->timestamp_last_tick, sd))
+ schedstat_inc(sd, lb_hot_gained[idle]);
+#endif
+
+ pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
+ pulled++;
+
+ /* We only want to steal up to the prescribed number of tasks. */
+ if (pulled < max_nr_move) {
if (curr != head)
goto skip_queue;
idx++;
goto skip_bitmap;
}
-out_unlock:
- spin_unlock(&busiest->lock);
out:
- ;
+ /*
+ * Right now, this is the only place pull_task() is called,
+ * so we can safely collect pull_task() stats here rather than
+ * inside pull_task().
+ */
+ schedstat_add(sd, lb_gained[idle], pulled);
+
+ if (all_pinned)
+ *all_pinned = pinned;
+ return pulled;
}
/*
- * One of the idle_cpu_tick() and busy_cpu_tick() functions will
- * get called every timer tick, on every CPU. Our balancing action
- * frequency and balancing agressivity depends on whether the CPU is
- * idle or not.
- *
- * busy-rebalance every 200 msecs. idle-rebalance every 1 msec. (or on
- * systems with HZ=100, every 10 msecs.)
- *
- * On NUMA, do a node-rebalance every 400 msecs.
+ * find_busiest_group finds and returns the busiest CPU group within the
+ * domain. It calculates and returns the number of tasks which should be
+ * moved to restore balance via the imbalance parameter.
*/
-#define IDLE_REBALANCE_TICK (HZ/1000 ?: 1)
-#define BUSY_REBALANCE_TICK (HZ/5 ?: 1)
-#define IDLE_NODE_REBALANCE_TICK (IDLE_REBALANCE_TICK * 5)
-#define BUSY_NODE_REBALANCE_TICK (BUSY_REBALANCE_TICK * 2)
-
-#ifdef CONFIG_NUMA
-static void balance_node(runqueue_t *this_rq, int idle, int this_cpu)
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+ unsigned long *imbalance, enum idle_type idle, int *sd_idle)
{
- int node = find_busiest_node(cpu_to_node(this_cpu));
+ struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
+ unsigned long max_load, avg_load, total_load, this_load, total_pwr;
+ unsigned long max_pull;
+ int load_idx;
+
+ max_load = this_load = total_load = total_pwr = 0;
+ if (idle == NOT_IDLE)
+ load_idx = sd->busy_idx;
+ else if (idle == NEWLY_IDLE)
+ load_idx = sd->newidle_idx;
+ else
+ load_idx = sd->idle_idx;
- if (node >= 0) {
- cpumask_t cpumask = node_to_cpumask(node);
- cpu_set(this_cpu, cpumask);
- spin_lock(&this_rq->lock);
- load_balance(this_rq, idle, cpumask);
- spin_unlock(&this_rq->lock);
- }
-}
-#endif
+ do {
+ unsigned long load;
+ int local_group;
+ int i;
-static void rebalance_tick(runqueue_t *this_rq, int idle)
-{
-#ifdef CONFIG_NUMA
- int this_cpu = smp_processor_id();
-#endif
- unsigned long j = jiffies;
+ local_group = cpu_isset(this_cpu, group->cpumask);
+
+ /* Tally up the load of all CPUs in the group */
+ avg_load = 0;
+
+ for_each_cpu_mask(i, group->cpumask) {
+ if (*sd_idle && !idle_cpu(i))
+ *sd_idle = 0;
+
+ /* Bias balancing toward cpus of our domain */
+ if (local_group)
+ load = target_load(i, load_idx);
+ else
+ load = source_load(i, load_idx);
+
+ avg_load += load;
+ }
+
+ total_load += avg_load;
+ total_pwr += group->cpu_power;
+
+ /* Adjust by relative CPU power of the group */
+ avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+ if (local_group) {
+ this_load = avg_load;
+ this = group;
+ } else if (avg_load > max_load) {
+ max_load = avg_load;
+ busiest = group;
+ }
+ group = group->next;
+ } while (group != sd->groups);
+
+ if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
+ goto out_balanced;
+
+ avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+
+ if (this_load >= avg_load ||
+ 100*max_load <= sd->imbalance_pct*this_load)
+ goto out_balanced;
/*
- * First do inter-node rebalancing, then intra-node rebalancing,
- * if both events happen in the same tick. The inter-node
- * rebalancing does not necessarily have to create a perfect
- * balance within the node, since we load-balance the most loaded
- * node with the current CPU. (ie. other CPUs in the local node
- * are not balanced.)
+ * We're trying to get all the cpus to the average_load, so we don't
+ * want to push ourselves above the average load, nor do we wish to
+ * reduce the max loaded cpu below the average load, as either of these
+ * actions would just result in more rebalancing later, and ping-pong
+ * tasks around. Thus we look for the minimum possible imbalance.
+ * Negative imbalances (*we* are more loaded than anyone else) will
+ * be counted as no imbalance for these purposes -- we can't fix that
+ * by pulling tasks to us. Be careful of negative numbers as they'll
+ * appear as very large values with unsigned longs.
*/
- if (idle) {
-#ifdef CONFIG_NUMA
- if (!(j % IDLE_NODE_REBALANCE_TICK))
- balance_node(this_rq, idle, this_cpu);
-#endif
- if (!(j % IDLE_REBALANCE_TICK)) {
- spin_lock(&this_rq->lock);
- load_balance(this_rq, idle, cpu_to_node_mask(this_cpu));
- spin_unlock(&this_rq->lock);
+
+ /* Don't want to pull so many tasks that a group would go idle */
+ max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE);
+
+ /* How much load to actually move to equalise the imbalance */
+ *imbalance = min(max_pull * busiest->cpu_power,
+ (avg_load - this_load) * this->cpu_power)
+ / SCHED_LOAD_SCALE;
+
+ if (*imbalance < SCHED_LOAD_SCALE) {
+ unsigned long pwr_now = 0, pwr_move = 0;
+ unsigned long tmp;
+
+ if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
+ *imbalance = 1;
+ return busiest;
}
- return;
- }
-#ifdef CONFIG_NUMA
- if (!(j % BUSY_NODE_REBALANCE_TICK))
- balance_node(this_rq, idle, this_cpu);
-#endif
- if (!(j % BUSY_REBALANCE_TICK)) {
- spin_lock(&this_rq->lock);
- load_balance(this_rq, idle, cpu_to_node_mask(this_cpu));
- spin_unlock(&this_rq->lock);
+
+ /*
+ * OK, we don't have enough imbalance to justify moving tasks,
+ * however we may be able to increase total CPU power used by
+ * moving them.
+ */
+
+ pwr_now += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load);
+ pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
+ pwr_now /= SCHED_LOAD_SCALE;
+
+ /* Amount of load we'd subtract */
+ tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power;
+ if (max_load > tmp)
+ pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE,
+ max_load - tmp);
+
+ /* Amount of load we'd add */
+ if (max_load*busiest->cpu_power <
+ SCHED_LOAD_SCALE*SCHED_LOAD_SCALE)
+ tmp = max_load*busiest->cpu_power/this->cpu_power;
+ else
+ tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
+ pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
+ pwr_move /= SCHED_LOAD_SCALE;
+
+ /* Move if we gain throughput */
+ if (pwr_move <= pwr_now)
+ goto out_balanced;
+
+ *imbalance = 1;
+ return busiest;
}
+
+ /* Get rid of the scaling factor, rounding down as we divide */
+ *imbalance = *imbalance / SCHED_LOAD_SCALE;
+ return busiest;
+
+out_balanced:
+
+ *imbalance = 0;
+ return NULL;
}
-#else
+
/*
- * on UP we do not need to balance between CPUs:
+ * find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
-static inline void rebalance_tick(runqueue_t *this_rq, int idle)
+static runqueue_t *find_busiest_queue(struct sched_group *group,
+ enum idle_type idle)
{
-}
-#endif
+ unsigned long load, max_load = 0;
+ runqueue_t *busiest = NULL;
+ int i;
-DEFINE_PER_CPU(struct kernel_stat, kstat);
+ for_each_cpu_mask(i, group->cpumask) {
+ load = source_load(i, 0);
-EXPORT_PER_CPU_SYMBOL(kstat);
+ if (load > max_load) {
+ max_load = load;
+ busiest = cpu_rq(i);
+ }
+ }
+
+ return busiest;
+}
/*
- * We place interactive tasks back into the active array, if possible.
- *
- * To guarantee that this does not starve expired tasks we ignore the
- * interactivity of a task if the first expired task had to wait more
- * than a 'reasonable' amount of time. This deadline timeout is
- * load-dependent, as the frequency of array switched decreases with
- * increasing number of running tasks. We also ignore the interactivity
- * if a better static_prio task has expired:
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
*/
-#define EXPIRED_STARVING(rq) \
- ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
- (jiffies - (rq)->expired_timestamp >= \
- STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
- ((rq)->curr->static_prio > (rq)->best_expired_prio))
+#define MAX_PINNED_INTERVAL 512
/*
- * This function gets called by the timer code, with HZ frequency.
- * We call it with interrupts disabled.
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
*
- * It also gets called by the fork code, when changing the parent's
- * timeslices.
+ * Called with this_rq unlocked.
*/
-void scheduler_tick(int user_ticks, int sys_ticks)
+static int load_balance(int this_cpu, runqueue_t *this_rq,
+ struct sched_domain *sd, enum idle_type idle)
{
- int cpu = smp_processor_id();
- struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- runqueue_t *rq = this_rq();
- task_t *p = current;
+ struct sched_group *group;
+ runqueue_t *busiest;
+ unsigned long imbalance;
+ int nr_moved, all_pinned = 0;
+ int active_balance = 0;
+ int sd_idle = 0;
- rq->timestamp_last_tick = sched_clock();
+ if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
+ sd_idle = 1;
- if (rcu_pending(cpu))
- rcu_check_callbacks(cpu, user_ticks);
+ schedstat_inc(sd, lb_cnt[idle]);
- /* note: this timer irq context must be accounted for as well */
- if (hardirq_count() - HARDIRQ_OFFSET) {
- cpustat->irq += sys_ticks;
- sys_ticks = 0;
- } else if (softirq_count()) {
- cpustat->softirq += sys_ticks;
- sys_ticks = 0;
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
+ if (!group) {
+ schedstat_inc(sd, lb_nobusyg[idle]);
+ goto out_balanced;
}
- if (p == rq->idle) {
- if (atomic_read(&rq->nr_iowait) > 0)
- cpustat->iowait += sys_ticks;
- else
- cpustat->idle += sys_ticks;
- rebalance_tick(rq, 1);
- return;
+ busiest = find_busiest_queue(group, idle);
+ if (!busiest) {
+ schedstat_inc(sd, lb_nobusyq[idle]);
+ goto out_balanced;
}
- if (TASK_NICE(p) > 0)
- cpustat->nice += user_ticks;
- else
- cpustat->user += user_ticks;
- cpustat->system += sys_ticks;
- /* Task might have expired already, but not scheduled off yet */
- if (p->array != rq->active) {
- set_tsk_need_resched(p);
- goto out;
- }
- spin_lock(&rq->lock);
- /*
- * The task was running during this tick - update the
- * time slice counter. Note: we do not update a thread's
- * priority until it either goes to sleep or uses up its
- * timeslice. This makes it possible for interactive tasks
- * to use up their timeslices at their highest priority levels.
- */
- if (unlikely(rt_task(p))) {
+ BUG_ON(busiest == this_rq);
+
+ schedstat_add(sd, lb_imbalance[idle], imbalance);
+
+ nr_moved = 0;
+ if (busiest->nr_running > 1) {
/*
- * RR tasks need a special form of timeslice management.
- * FIFO tasks have no timeslices.
+ * Attempt to move tasks. If find_busiest_group has found
+ * an imbalance but busiest->nr_running <= 1, the group is
+ * still unbalanced. nr_moved simply stays zero, so it is
+ * correctly treated as an imbalance.
*/
- if ((p->policy == SCHED_RR) && !--p->time_slice) {
- p->time_slice = task_timeslice(p);
- p->first_time_slice = 0;
- set_tsk_need_resched(p);
+ double_rq_lock(this_rq, busiest);
+ nr_moved = move_tasks(this_rq, this_cpu, busiest,
+ imbalance, sd, idle, &all_pinned);
+ double_rq_unlock(this_rq, busiest);
+
+ /* All tasks on this runqueue were pinned by CPU affinity */
+ if (unlikely(all_pinned))
+ goto out_balanced;
+ }
- /* put it at the end of the queue: */
- dequeue_task(p, rq->active);
- enqueue_task(p, rq->active);
+ if (!nr_moved) {
+ schedstat_inc(sd, lb_failed[idle]);
+ sd->nr_balance_failed++;
+
+ if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
+
+ spin_lock(&busiest->lock);
+
+ /* don't kick the migration_thread, if the curr
+ * task on busiest cpu can't be moved to this_cpu
+ */
+ if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+ spin_unlock(&busiest->lock);
+ all_pinned = 1;
+ goto out_one_pinned;
+ }
+
+ if (!busiest->active_balance) {
+ busiest->active_balance = 1;
+ busiest->push_cpu = this_cpu;
+ active_balance = 1;
+ }
+ spin_unlock(&busiest->lock);
+ if (active_balance)
+ wake_up_process(busiest->migration_thread);
+
+ /*
+ * We've kicked active balancing, reset the failure
+ * counter.
+ */
+ sd->nr_balance_failed = sd->cache_nice_tries+1;
}
- goto out_unlock;
- }
- if (!--p->time_slice) {
- dequeue_task(p, rq->active);
- set_tsk_need_resched(p);
- p->prio = effective_prio(p);
- p->time_slice = task_timeslice(p);
- p->first_time_slice = 0;
+ } else
+ sd->nr_balance_failed = 0;
- if (!rq->expired_timestamp)
- rq->expired_timestamp = jiffies;
- if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
- enqueue_task(p, rq->expired);
- if (p->static_prio < rq->best_expired_prio)
- rq->best_expired_prio = p->static_prio;
- } else
- enqueue_task(p, rq->active);
+ if (likely(!active_balance)) {
+ /* We were unbalanced, so reset the balancing interval */
+ sd->balance_interval = sd->min_interval;
} else {
/*
- * Prevent a too long timeslice allowing a task to monopolize
- * the CPU. We do this by splitting up the timeslice into
- * smaller pieces.
- *
- * Note: this does not mean the task's timeslices expire or
- * get lost in any way, they just might be preempted by
- * another task of equal priority. (one with higher
- * priority would have preempted this task already.) We
- * requeue this task to the end of the list on this priority
- * level, which is in essence a round-robin of tasks with
- * equal priority.
- *
- * This only applies to tasks in the interactive
- * delta range with at least TIMESLICE_GRANULARITY to requeue.
+ * If we've begun active balancing, start to back off. This
+ * case may not be covered by the all_pinned logic if there
+ * is only 1 task on the busy runqueue (because we don't call
+ * move_tasks).
*/
- if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
- p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
- (p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
- (p->array == rq->active)) {
-
- dequeue_task(p, rq->active);
- set_tsk_need_resched(p);
- p->prio = effective_prio(p);
- enqueue_task(p, rq->active);
- }
+ if (sd->balance_interval < sd->max_interval)
+ sd->balance_interval *= 2;
}
-out_unlock:
- spin_unlock(&rq->lock);
-out:
- rebalance_tick(rq, 0);
+
+ if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ return -1;
+ return nr_moved;
+
+out_balanced:
+ schedstat_inc(sd, lb_balanced[idle]);
+
+ sd->nr_balance_failed = 0;
+
+out_one_pinned:
+ /* tune up the balancing interval */
+ if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+ (sd->balance_interval < sd->max_interval))
+ sd->balance_interval *= 2;
+
+ if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ return -1;
+ return 0;
}
/*
- * schedule() is the main scheduler function.
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ *
+ * Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
+ * this_rq is locked.
*/
-asmlinkage void __sched schedule(void)
+static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
+ struct sched_domain *sd)
{
- long *switch_count;
- task_t *prev, *next;
- runqueue_t *rq;
- prio_array_t *array;
- struct list_head *queue;
- unsigned long long now;
- unsigned long run_time;
- int idx;
+ struct sched_group *group;
+ runqueue_t *busiest = NULL;
+ unsigned long imbalance;
+ int nr_moved = 0;
+ int sd_idle = 0;
+
+ if (sd->flags & SD_SHARE_CPUPOWER)
+ sd_idle = 1;
+
+ schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
+ group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
+ if (!group) {
+ schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
+ goto out_balanced;
+ }
- /*
- * Test if we are atomic. Since do_exit() needs to call into
- * schedule() atomically, we ignore that path for now.
- * Otherwise, whine if we are scheduling when we should not be.
- */
- if (likely(!(current->state & (TASK_DEAD | TASK_ZOMBIE)))) {
- if (unlikely(in_atomic())) {
- printk(KERN_ERR "bad: scheduling while atomic!\n");
- dump_stack();
- }
+ busiest = find_busiest_queue(group, NEWLY_IDLE);
+ if (!busiest) {
+ schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
+ goto out_balanced;
}
-need_resched:
- preempt_disable();
- prev = current;
- rq = this_rq();
+ BUG_ON(busiest == this_rq);
- release_kernel_lock(prev);
- now = sched_clock();
- if (likely(now - prev->timestamp < NS_MAX_SLEEP_AVG))
- run_time = now - prev->timestamp;
- else
- run_time = NS_MAX_SLEEP_AVG;
+ schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
- /*
- * Tasks with interactive credits get charged less run_time
- * at high sleep_avg to delay them losing their interactive
- * status
- */
- if (HIGH_CREDIT(prev))
- run_time /= (CURRENT_BONUS(prev) ? : 1);
+ nr_moved = 0;
+ if (busiest->nr_running > 1) {
+ /* Attempt to move tasks */
+ double_lock_balance(this_rq, busiest);
+ nr_moved = move_tasks(this_rq, this_cpu, busiest,
+ imbalance, sd, NEWLY_IDLE, NULL);
+ spin_unlock(&busiest->lock);
+ }
- spin_lock_irq(&rq->lock);
+ if (!nr_moved) {
+ schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
+ if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ return -1;
+ } else
+ sd->nr_balance_failed = 0;
- /*
- * if entering off of a kernel preemption go straight
- * to picking the next task.
- */
- switch_count = &prev->nivcsw;
- if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
- switch_count = &prev->nvcsw;
- if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
- unlikely(signal_pending(prev))))
- prev->state = TASK_RUNNING;
- else
- deactivate_task(prev, rq);
- }
+ return nr_moved;
- if (unlikely(!rq->nr_running)) {
-#ifdef CONFIG_SMP
- load_balance(rq, 1, cpu_to_node_mask(smp_processor_id()));
-#endif
- if (!rq->nr_running) {
- next = rq->idle;
- rq->expired_timestamp = 0;
- goto switch_tasks;
- }
- }
+out_balanced:
+ schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
+ if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ return -1;
+ sd->nr_balance_failed = 0;
+ return 0;
+}
- array = rq->active;
- if (unlikely(!array->nr_active)) {
- /*
- * Switch the active and expired arrays.
- */
- rq->active = rq->expired;
- rq->expired = array;
- array = rq->active;
- rq->expired_timestamp = 0;
- rq->best_expired_prio = MAX_PRIO;
+/*
+ * idle_balance is called by schedule() if this_cpu is about to become
+ * idle. Attempts to pull tasks from other CPUs.
+ */
+static void idle_balance(int this_cpu, runqueue_t *this_rq)
+{
+ struct sched_domain *sd;
+
+ for_each_domain(this_cpu, sd) {
+ if (sd->flags & SD_BALANCE_NEWIDLE) {
+ if (load_balance_newidle(this_cpu, this_rq, sd)) {
+ /* We've pulled tasks over so stop searching */
+ break;
+ }
+ }
}
+}
- idx = sched_find_first_bit(array->bitmap);
- queue = array->queue + idx;
- next = list_entry(queue->next, task_t, run_list);
+/*
+ * active_load_balance is run by migration threads. It pushes running tasks
+ * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
+ * running on each physical CPU where possible, and avoids physical /
+ * logical imbalances.
+ *
+ * Called with busiest_rq locked.
+ */
+static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu)
+{
+ struct sched_domain *sd;
+ runqueue_t *target_rq;
+ int target_cpu = busiest_rq->push_cpu;
- if (!rt_task(next) && next->activated > 0) {
- unsigned long long delta = now - next->timestamp;
+ if (busiest_rq->nr_running <= 1)
+ /* no task to move */
+ return;
- if (next->activated == 1)
- delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
+ target_rq = cpu_rq(target_cpu);
- array = next->array;
- dequeue_task(next, array);
- recalc_task_prio(next, next->timestamp + delta);
- enqueue_task(next, array);
- }
- next->activated = 0;
-switch_tasks:
- prefetch(next);
- clear_tsk_need_resched(prev);
- RCU_qsctr(task_cpu(prev))++;
+ /*
+ * This condition is "impossible", if it occurs
+ * we need to fix it. Originally reported by
+ * Bjorn Helgaas on a 128-cpu setup.
+ */
+ BUG_ON(busiest_rq == target_rq);
- prev->sleep_avg -= run_time;
- if ((long)prev->sleep_avg <= 0) {
- prev->sleep_avg = 0;
- if (!(HIGH_CREDIT(prev) || LOW_CREDIT(prev)))
- prev->interactive_credit--;
- }
- prev->timestamp = now;
+ /* move a task from busiest_rq to target_rq */
+ double_lock_balance(busiest_rq, target_rq);
- if (likely(prev != next)) {
- next->timestamp = now;
- rq->nr_switches++;
- rq->curr = next;
- ++*switch_count;
+ /* Search for an sd spanning us and the target CPU. */
+ for_each_domain(target_cpu, sd)
+ if ((sd->flags & SD_LOAD_BALANCE) &&
+ cpu_isset(busiest_cpu, sd->span))
+ break;
- prepare_arch_switch(rq, next);
- prev = context_switch(rq, prev, next);
- barrier();
+ if (unlikely(sd == NULL))
+ goto out;
- finish_task_switch(prev);
- } else
- spin_unlock_irq(&rq->lock);
+ schedstat_inc(sd, alb_cnt);
- reacquire_kernel_lock(current);
- preempt_enable_no_resched();
- if (test_thread_flag(TIF_NEED_RESCHED))
- goto need_resched;
+ if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL))
+ schedstat_inc(sd, alb_pushed);
+ else
+ schedstat_inc(sd, alb_failed);
+out:
+ spin_unlock(&target_rq->lock);
}
-EXPORT_SYMBOL(schedule);
-
-#ifdef CONFIG_PREEMPT
/*
- * this is is the entry point to schedule() from in-kernel preemption
- * off of preempt_enable. Kernel preemptions off return from interrupt
- * occur there and call schedule directly.
+ * rebalance_tick will get called every timer tick, on every CPU.
+ *
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
*/
-asmlinkage void __sched preempt_schedule(void)
-{
- struct thread_info *ti = current_thread_info();
- /*
- * If there is a non-zero preempt_count or interrupts are disabled,
- * we do not want to preempt the current task. Just return..
- */
- if (unlikely(ti->preempt_count || irqs_disabled()))
- return;
+/* Don't have all balancing operations going off at once */
+#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)
-need_resched:
- ti->preempt_count = PREEMPT_ACTIVE;
- schedule();
- ti->preempt_count = 0;
+static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
+ enum idle_type idle)
+{
+ unsigned long old_load, this_load;
+ unsigned long j = jiffies + CPU_OFFSET(this_cpu);
+ struct sched_domain *sd;
+ int i;
- /* we could miss a preemption opportunity between schedule and now */
- barrier();
- if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
- goto need_resched;
-}
+ this_load = this_rq->nr_running * SCHED_LOAD_SCALE;
+ /* Update our load */
+ for (i = 0; i < 3; i++) {
+ unsigned long new_load = this_load;
+ int scale = 1 << i;
+ old_load = this_rq->cpu_load[i];
+ /*
+ * Round up the averaging division if load is increasing. This
+ * prevents us from getting stuck on 9 if the load is 10, for
+ * example.
+ */
+ if (new_load > old_load)
+ new_load += scale-1;
+ this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale;
+ }
-EXPORT_SYMBOL(preempt_schedule);
-#endif /* CONFIG_PREEMPT */
+ for_each_domain(this_cpu, sd) {
+ unsigned long interval;
-int default_wake_function(wait_queue_t *curr, unsigned mode, int sync)
-{
- task_t *p = curr->task;
- return try_to_wake_up(p, mode, sync);
-}
+ if (!(sd->flags & SD_LOAD_BALANCE))
+ continue;
-EXPORT_SYMBOL(default_wake_function);
+ interval = sd->balance_interval;
+ if (idle != SCHED_IDLE)
+ interval *= sd->busy_factor;
+
+ /* scale ms to jiffies */
+ interval = msecs_to_jiffies(interval);
+ if (unlikely(!interval))
+ interval = 1;
+ if (j - sd->last_balance >= interval) {
+ if (load_balance(this_cpu, this_rq, sd, idle)) {
+ /*
+ * We've pulled tasks over so either we're no
+ * longer idle, or one of our SMT siblings is
+ * not idle.
+ */
+ idle = NOT_IDLE;
+ }
+ sd->last_balance += interval;
+ }
+ }
+}
+#else
/*
- * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
- * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
- *
- * There are circumstances in which we can try to wake a task which has already
- * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
- * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ * on UP we do not need to balance between CPUs:
*/
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync)
+static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
{
- struct list_head *tmp, *next;
+}
+static inline void idle_balance(int cpu, runqueue_t *rq)
+{
+}
+#endif
- list_for_each_safe(tmp, next, &q->task_list) {
- wait_queue_t *curr;
- unsigned flags;
- curr = list_entry(tmp, wait_queue_t, task_list);
- flags = curr->flags;
- if (curr->func(curr, mode, sync) &&
- (flags & WQ_FLAG_EXCLUSIVE) &&
- !--nr_exclusive)
- break;
+static inline int wake_priority_sleeper(runqueue_t *rq)
+{
+ int ret = 0;
+#ifdef CONFIG_SCHED_SMT
+ spin_lock(&rq->lock);
+ /*
+ * If an SMT sibling task has been put to sleep for priority
+ * reasons reschedule the idle task to see if it can now run.
+ */
+ if (rq->nr_running) {
+ resched_task(rq->idle);
+ ret = 1;
}
+ spin_unlock(&rq->lock);
+#endif
+ return ret;
}
-/**
- * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
+DEFINE_PER_CPU(struct kernel_stat, kstat);
+
+EXPORT_PER_CPU_SYMBOL(kstat);
+
+/*
+ * This is called on clock ticks and on context switches.
+ * Bank in p->sched_time the ns elapsed since the last tick or switch.
*/
-void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+static inline void update_cpu_clock(task_t *p, runqueue_t *rq,
+ unsigned long long now)
{
- unsigned long flags;
-
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_common(q, mode, nr_exclusive, 0);
- spin_unlock_irqrestore(&q->lock, flags);
+ unsigned long long last = max(p->timestamp, rq->timestamp_last_tick);
+ p->sched_time += now - last;
}
-EXPORT_SYMBOL(__wake_up);
-
/*
- * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ * Return current->sched_time plus any more ns on the sched_clock
+ * that have not yet been banked.
*/
-void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+unsigned long long current_sched_time(const task_t *tsk)
{
- __wake_up_common(q, mode, 1, 0);
+ unsigned long long ns;
+ unsigned long flags;
+ local_irq_save(flags);
+ ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick);
+ ns = tsk->sched_time + (sched_clock() - ns);
+ local_irq_restore(flags);
+ return ns;
}
-/**
- * __wake_up - sync- wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
- *
- * The sync wakeup differs that the waker knows that it will schedule
- * away soon, so while the target thread will be woken up, it will not
- * be migrated to another CPU - ie. the two threads are 'synchronized'
- * with each other. This can prevent needless bouncing between CPUs.
+/*
+ * We place interactive tasks back into the active array, if possible.
*
- * On UP it can prevent extra preemption.
+ * To guarantee that this does not starve expired tasks we ignore the
+ * interactivity of a task if the first expired task had to wait more
+ * than a 'reasonable' amount of time. This deadline timeout is
+ * load-dependent, as the frequency of array switched decreases with
+ * increasing number of running tasks. We also ignore the interactivity
+ * if a better static_prio task has expired:
+ */
+#define EXPIRED_STARVING(rq) \
+ ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
+ (jiffies - (rq)->expired_timestamp >= \
+ STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
+ ((rq)->curr->static_prio > (rq)->best_expired_prio))
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in user space since the last update
*/
-void fastcall __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void account_user_time(struct task_struct *p, cputime_t cputime)
{
- unsigned long flags;
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ struct vx_info *vxi = p->vx_info; /* p is _always_ current */
+ cputime64_t tmp;
+ int nice = (TASK_NICE(p) > 0);
- if (unlikely(!q))
- return;
+ p->utime = cputime_add(p->utime, cputime);
+ vx_account_user(vxi, cputime, nice);
- spin_lock_irqsave(&q->lock, flags);
- if (likely(nr_exclusive))
- __wake_up_common(q, mode, nr_exclusive, 1);
+ /* Add user time to cpustat. */
+ tmp = cputime_to_cputime64(cputime);
+ if (nice)
+ cpustat->nice = cputime64_add(cpustat->nice, tmp);
else
- __wake_up_common(q, mode, nr_exclusive, 0);
- spin_unlock_irqrestore(&q->lock, flags);
+ cpustat->user = cputime64_add(cpustat->user, tmp);
}
-EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
-void fastcall complete(struct completion *x)
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+ cputime_t cputime)
{
- unsigned long flags;
-
- spin_lock_irqsave(&x->wait.lock, flags);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ struct vx_info *vxi = p->vx_info; /* p is _always_ current */
+ runqueue_t *rq = this_rq();
+ cputime64_t tmp;
+
+ p->stime = cputime_add(p->stime, cputime);
+ vx_account_system(vxi, cputime, (p == rq->idle));
+
+ /* Add system time to cpustat. */
+ tmp = cputime_to_cputime64(cputime);
+ if (hardirq_count() - hardirq_offset)
+ cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ else if (softirq_count())
+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ else if (p != rq->idle)
+ cpustat->system = cputime64_add(cpustat->system, tmp);
+ else if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
+ else
+ cpustat->idle = cputime64_add(cpustat->idle, tmp);
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @p: the process from which the cpu time has been stolen
+ * @steal: the cpu time spent in involuntary wait
+ */
+void account_steal_time(struct task_struct *p, cputime_t steal)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ cputime64_t tmp = cputime_to_cputime64(steal);
+ runqueue_t *rq = this_rq();
+
+ if (p == rq->idle) {
+ p->stime = cputime_add(p->stime, steal);
+ if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
+ else
+ cpustat->idle = cputime64_add(cpustat->idle, tmp);
+ } else
+ cpustat->steal = cputime64_add(cpustat->steal, tmp);
+}
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled.
+ *
+ * It also gets called by the fork code, when changing the parent's
+ * timeslices.
+ */
+void scheduler_tick(void)
+{
+ int cpu = smp_processor_id();
+ runqueue_t *rq = this_rq();
+ task_t *p = current;
+ unsigned long long now = sched_clock();
+
+ update_cpu_clock(p, rq, now);
+
+ rq->timestamp_last_tick = now;
+
+ if (p == rq->idle) {
+ if (wake_priority_sleeper(rq))
+ goto out;
+#ifdef CONFIG_VSERVER_HARDCPU_IDLE
+ if (!--rq->idle_tokens && !list_empty(&rq->hold_queue))
+ set_need_resched();
+#endif
+ rebalance_tick(cpu, rq, SCHED_IDLE);
+ return;
+ }
+
+ /* Task might have expired already, but not scheduled off yet */
+ if (p->array != rq->active) {
+ set_tsk_need_resched(p);
+ goto out;
+ }
+ spin_lock(&rq->lock);
+ /*
+ * The task was running during this tick - update the
+ * time slice counter. Note: we do not update a thread's
+ * priority until it either goes to sleep or uses up its
+ * timeslice. This makes it possible for interactive tasks
+ * to use up their timeslices at their highest priority levels.
+ */
+ if (rt_task(p)) {
+ /*
+ * RR tasks need a special form of timeslice management.
+ * FIFO tasks have no timeslices.
+ */
+ if ((p->policy == SCHED_RR) && !--p->time_slice) {
+ p->time_slice = task_timeslice(p);
+ p->first_time_slice = 0;
+ set_tsk_need_resched(p);
+
+ /* put it at the end of the queue: */
+ requeue_task(p, rq->active);
+ }
+ goto out_unlock;
+ }
+ if (vx_need_resched(p)) {
+ dequeue_task(p, rq->active);
+ set_tsk_need_resched(p);
+ p->prio = effective_prio(p);
+ p->time_slice = task_timeslice(p);
+ p->first_time_slice = 0;
+
+ if (!rq->expired_timestamp)
+ rq->expired_timestamp = jiffies;
+ if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
+ enqueue_task(p, rq->expired);
+ if (p->static_prio < rq->best_expired_prio)
+ rq->best_expired_prio = p->static_prio;
+ } else
+ enqueue_task(p, rq->active);
+ } else {
+ /*
+ * Prevent a too long timeslice allowing a task to monopolize
+ * the CPU. We do this by splitting up the timeslice into
+ * smaller pieces.
+ *
+ * Note: this does not mean the task's timeslices expire or
+ * get lost in any way, they just might be preempted by
+ * another task of equal priority. (one with higher
+ * priority would have preempted this task already.) We
+ * requeue this task to the end of the list on this priority
+ * level, which is in essence a round-robin of tasks with
+ * equal priority.
+ *
+ * This only applies to tasks in the interactive
+ * delta range with at least TIMESLICE_GRANULARITY to requeue.
+ */
+ if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
+ p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
+ (p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
+ (p->array == rq->active)) {
+
+ requeue_task(p, rq->active);
+ set_tsk_need_resched(p);
+ }
+ }
+out_unlock:
+ spin_unlock(&rq->lock);
+out:
+ rebalance_tick(cpu, rq, NOT_IDLE);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static inline void wakeup_busy_runqueue(runqueue_t *rq)
+{
+ /* If an SMT runqueue is sleeping due to priority reasons wake it up */
+ if (rq->curr == rq->idle && rq->nr_running)
+ resched_task(rq->idle);
+}
+
+static void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
+{
+ struct sched_domain *tmp, *sd = NULL;
+ cpumask_t sibling_map;
+ int i;
+
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
+
+ if (!sd)
+ return;
+
+ /*
+ * Unlock the current runqueue because we have to lock in
+ * CPU order to avoid deadlocks. Caller knows that we might
+ * unlock. We keep IRQs disabled.
+ */
+ spin_unlock(&this_rq->lock);
+
+ sibling_map = sd->span;
+
+ for_each_cpu_mask(i, sibling_map)
+ spin_lock(&cpu_rq(i)->lock);
+ /*
+ * We clear this CPU from the mask. This both simplifies the
+ * inner loop and keps this_rq locked when we exit:
+ */
+ cpu_clear(this_cpu, sibling_map);
+
+ for_each_cpu_mask(i, sibling_map) {
+ runqueue_t *smt_rq = cpu_rq(i);
+
+ wakeup_busy_runqueue(smt_rq);
+ }
+
+ for_each_cpu_mask(i, sibling_map)
+ spin_unlock(&cpu_rq(i)->lock);
+ /*
+ * We exit with this_cpu's rq still held and IRQs
+ * still disabled:
+ */
+}
+
+/*
+ * number of 'lost' timeslices this task wont be able to fully
+ * utilize, if another task runs on a sibling. This models the
+ * slowdown effect of other tasks running on siblings:
+ */
+static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd)
+{
+ return p->time_slice * (100 - sd->per_cpu_gain) / 100;
+}
+
+static int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
+{
+ struct sched_domain *tmp, *sd = NULL;
+ cpumask_t sibling_map;
+ prio_array_t *array;
+ int ret = 0, i;
+ task_t *p;
+
+ for_each_domain(this_cpu, tmp)
+ if (tmp->flags & SD_SHARE_CPUPOWER)
+ sd = tmp;
+
+ if (!sd)
+ return 0;
+
+ /*
+ * The same locking rules and details apply as for
+ * wake_sleeping_dependent():
+ */
+ spin_unlock(&this_rq->lock);
+ sibling_map = sd->span;
+ for_each_cpu_mask(i, sibling_map)
+ spin_lock(&cpu_rq(i)->lock);
+ cpu_clear(this_cpu, sibling_map);
+
+ /*
+ * Establish next task to be run - it might have gone away because
+ * we released the runqueue lock above:
+ */
+ if (!this_rq->nr_running)
+ goto out_unlock;
+ array = this_rq->active;
+ if (!array->nr_active)
+ array = this_rq->expired;
+ BUG_ON(!array->nr_active);
+
+ p = list_entry(array->queue[sched_find_first_bit(array->bitmap)].next,
+ task_t, run_list);
+
+ for_each_cpu_mask(i, sibling_map) {
+ runqueue_t *smt_rq = cpu_rq(i);
+ task_t *smt_curr = smt_rq->curr;
+
+ /* Kernel threads do not participate in dependent sleeping */
+ if (!p->mm || !smt_curr->mm || rt_task(p))
+ goto check_smt_task;
+
+ /*
+ * If a user task with lower static priority than the
+ * running task on the SMT sibling is trying to schedule,
+ * delay it till there is proportionately less timeslice
+ * left of the sibling task to prevent a lower priority
+ * task from using an unfair proportion of the
+ * physical cpu's resources. -ck
+ */
+ if (rt_task(smt_curr)) {
+ /*
+ * With real time tasks we run non-rt tasks only
+ * per_cpu_gain% of the time.
+ */
+ if ((jiffies % DEF_TIMESLICE) >
+ (sd->per_cpu_gain * DEF_TIMESLICE / 100))
+ ret = 1;
+ } else
+ if (smt_curr->static_prio < p->static_prio &&
+ !TASK_PREEMPTS_CURR(p, smt_rq) &&
+ smt_slice(smt_curr, sd) > task_timeslice(p))
+ ret = 1;
+
+check_smt_task:
+ if ((!smt_curr->mm && smt_curr != smt_rq->idle) ||
+ rt_task(smt_curr))
+ continue;
+ if (!p->mm) {
+ wakeup_busy_runqueue(smt_rq);
+ continue;
+ }
+
+ /*
+ * Reschedule a lower priority task on the SMT sibling for
+ * it to be put to sleep, or wake it up if it has been put to
+ * sleep for priority reasons to see if it should run now.
+ */
+ if (rt_task(p)) {
+ if ((jiffies % DEF_TIMESLICE) >
+ (sd->per_cpu_gain * DEF_TIMESLICE / 100))
+ resched_task(smt_curr);
+ } else {
+ if (TASK_PREEMPTS_CURR(p, smt_rq) &&
+ smt_slice(p, sd) > task_timeslice(smt_curr))
+ resched_task(smt_curr);
+ else
+ wakeup_busy_runqueue(smt_rq);
+ }
+ }
+out_unlock:
+ for_each_cpu_mask(i, sibling_map)
+ spin_unlock(&cpu_rq(i)->lock);
+ return ret;
+}
+#else
+static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
+{
+}
+
+static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
+{
+ return 0;
+}
+#endif
+
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
+
+void fastcall add_preempt_count(int val)
+{
+ /*
+ * Underflow?
+ */
+ BUG_ON((preempt_count() < 0));
+ preempt_count() += val;
+ /*
+ * Spinlock count overflowing soon?
+ */
+ BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
+}
+EXPORT_SYMBOL(add_preempt_count);
+
+void fastcall sub_preempt_count(int val)
+{
+ /*
+ * Underflow?
+ */
+ BUG_ON(val > preempt_count());
+ /*
+ * Is the spinlock portion underflowing?
+ */
+ BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK));
+ preempt_count() -= val;
+}
+EXPORT_SYMBOL(sub_preempt_count);
+
+#endif
+
+static inline int interactive_sleep(enum sleep_type sleep_type)
+{
+ return (sleep_type == SLEEP_INTERACTIVE ||
+ sleep_type == SLEEP_INTERRUPTED);
+}
+
+/*
+ * schedule() is the main scheduler function.
+ */
+asmlinkage void __sched schedule(void)
+{
+ long *switch_count;
+ task_t *prev, *next;
+ runqueue_t *rq;
+ prio_array_t *array;
+ struct list_head *queue;
+ unsigned long long now;
+ unsigned long run_time;
+ int cpu, idx, new_prio;
+ struct vx_info *vxi;
+#ifdef CONFIG_VSERVER_HARDCPU
+ int maxidle = -HZ;
+#endif
+
+ /*
+ * Test if we are atomic. Since do_exit() needs to call into
+ * schedule() atomically, we ignore that path for now.
+ * Otherwise, whine if we are scheduling when we should not be.
+ */
+ if (unlikely(in_atomic() && !current->exit_state)) {
+ printk(KERN_ERR "BUG: scheduling while atomic: "
+ "%s/0x%08x/%d\n",
+ current->comm, preempt_count(), current->pid);
+ dump_stack();
+ }
+ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
+
+need_resched:
+ preempt_disable();
+ prev = current;
+ release_kernel_lock(prev);
+need_resched_nonpreemptible:
+ rq = this_rq();
+
+ /*
+ * The idle thread is not allowed to schedule!
+ * Remove this check after it has been exercised a bit.
+ */
+ if (unlikely(prev == rq->idle) && prev->state != TASK_RUNNING) {
+ printk(KERN_ERR "bad: scheduling from the idle thread!\n");
+ dump_stack();
+ }
+
+ schedstat_inc(rq, sched_cnt);
+ now = sched_clock();
+ if (likely((long long)(now - prev->timestamp) < NS_MAX_SLEEP_AVG)) {
+ run_time = now - prev->timestamp;
+ if (unlikely((long long)(now - prev->timestamp) < 0))
+ run_time = 0;
+ } else
+ run_time = NS_MAX_SLEEP_AVG;
+
+ /*
+ * Tasks charged proportionately less run_time at high sleep_avg to
+ * delay them losing their interactive status
+ */
+ run_time /= (CURRENT_BONUS(prev) ? : 1);
+
+ spin_lock_irq(&rq->lock);
+
+ if (unlikely(prev->flags & PF_DEAD))
+ prev->state = EXIT_DEAD;
+
+ switch_count = &prev->nivcsw;
+ if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+ switch_count = &prev->nvcsw;
+ if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
+ unlikely(signal_pending(prev))))
+ prev->state = TASK_RUNNING;
+ else {
+ if (prev->state == TASK_UNINTERRUPTIBLE) {
+ rq->nr_uninterruptible++;
+ vx_uninterruptible_inc(prev);
+ }
+ deactivate_task(prev, rq);
+ }
+ }
+
+#ifdef CONFIG_VSERVER_HARDCPU
+ if (!list_empty(&rq->hold_queue)) {
+ struct list_head *l, *n;
+ int ret;
+
+ vxi = NULL;
+ list_for_each_safe(l, n, &rq->hold_queue) {
+ next = list_entry(l, task_t, run_list);
+ if (vxi == next->vx_info)
+ continue;
+
+ vxi = next->vx_info;
+ ret = vx_tokens_recalc(vxi);
+
+ if (ret > 0) {
+ vx_unhold_task(vxi, next, rq);
+ break;
+ }
+ if ((ret < 0) && (maxidle < ret))
+ maxidle = ret;
+ }
+ }
+ rq->idle_tokens = -maxidle;
+
+pick_next:
+#endif
+
+ cpu = smp_processor_id();
+ if (unlikely(!rq->nr_running)) {
+go_idle:
+ idle_balance(cpu, rq);
+ if (!rq->nr_running) {
+ next = rq->idle;
+ rq->expired_timestamp = 0;
+ wake_sleeping_dependent(cpu, rq);
+ /*
+ * wake_sleeping_dependent() might have released
+ * the runqueue, so break out if we got new
+ * tasks meanwhile:
+ */
+ if (!rq->nr_running)
+ goto switch_tasks;
+ }
+ } else {
+ if (dependent_sleeper(cpu, rq)) {
+ next = rq->idle;
+ goto switch_tasks;
+ }
+ /*
+ * dependent_sleeper() releases and reacquires the runqueue
+ * lock, hence go into the idle loop if the rq went
+ * empty meanwhile:
+ */
+ if (unlikely(!rq->nr_running))
+ goto go_idle;
+ }
+
+ array = rq->active;
+ if (unlikely(!array->nr_active)) {
+ /*
+ * Switch the active and expired arrays.
+ */
+ schedstat_inc(rq, sched_switch);
+ rq->active = rq->expired;
+ rq->expired = array;
+ array = rq->active;
+ rq->expired_timestamp = 0;
+ rq->best_expired_prio = MAX_PRIO;
+ }
+
+ idx = sched_find_first_bit(array->bitmap);
+ queue = array->queue + idx;
+ next = list_entry(queue->next, task_t, run_list);
+
+ vxi = next->vx_info;
+#ifdef CONFIG_VSERVER_HARDCPU
+ if (vx_info_flags(vxi, VXF_SCHED_PAUSE|VXF_SCHED_HARD, 0)) {
+ int ret = vx_tokens_recalc(vxi);
+
+ if (unlikely(ret <= 0)) {
+ if (ret && (rq->idle_tokens > -ret))
+ rq->idle_tokens = -ret;
+ vx_hold_task(vxi, next, rq);
+ goto pick_next;
+ }
+ } else /* well, looks ugly but not as ugly as the ifdef-ed version */
+#endif
+ if (vx_info_flags(vxi, VXF_SCHED_PRIO, 0))
+ vx_tokens_recalc(vxi);
+
+ if (!rt_task(next) && interactive_sleep(next->sleep_type)) {
+ unsigned long long delta = now - next->timestamp;
+ if (unlikely((long long)(now - next->timestamp) < 0))
+ delta = 0;
+
+ if (next->sleep_type == SLEEP_INTERACTIVE)
+ delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
+
+ array = next->array;
+ new_prio = recalc_task_prio(next, next->timestamp + delta);
+
+ if (unlikely(next->prio != new_prio)) {
+ dequeue_task(next, array);
+ next->prio = new_prio;
+ enqueue_task(next, array);
+ }
+ }
+ next->sleep_type = SLEEP_NORMAL;
+switch_tasks:
+ if (next == rq->idle)
+ schedstat_inc(rq, sched_goidle);
+ prefetch(next);
+ prefetch_stack(next);
+ clear_tsk_need_resched(prev);
+ rcu_qsctr_inc(task_cpu(prev));
+
+ update_cpu_clock(prev, rq, now);
+
+ prev->sleep_avg -= run_time;
+ if ((long)prev->sleep_avg <= 0)
+ prev->sleep_avg = 0;
+ prev->timestamp = prev->last_ran = now;
+
+ sched_info_switch(prev, next);
+ if (likely(prev != next)) {
+ next->timestamp = now;
+ rq->nr_switches++;
+ rq->curr = next;
+ ++*switch_count;
+
+ prepare_task_switch(rq, next);
+ prev = context_switch(rq, prev, next);
+ barrier();
+ /*
+ * this_rq must be evaluated again because prev may have moved
+ * CPUs since it called schedule(), thus the 'rq' on its stack
+ * frame will be invalid.
+ */
+ finish_task_switch(this_rq(), prev);
+ } else
+ spin_unlock_irq(&rq->lock);
+
+ prev = current;
+ if (unlikely(reacquire_kernel_lock(prev) < 0))
+ goto need_resched_nonpreemptible;
+ preempt_enable_no_resched();
+ if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+ goto need_resched;
+}
+
+EXPORT_SYMBOL(schedule);
+
+#ifdef CONFIG_PREEMPT
+/*
+ * this is is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable. Kernel preemptions off return from interrupt
+ * occur there and call schedule directly.
+ */
+asmlinkage void __sched preempt_schedule(void)
+{
+ struct thread_info *ti = current_thread_info();
+#ifdef CONFIG_PREEMPT_BKL
+ struct task_struct *task = current;
+ int saved_lock_depth;
+#endif
+ /*
+ * If there is a non-zero preempt_count or interrupts are disabled,
+ * we do not want to preempt the current task. Just return..
+ */
+ if (unlikely(ti->preempt_count || irqs_disabled()))
+ return;
+
+need_resched:
+ add_preempt_count(PREEMPT_ACTIVE);
+ /*
+ * We keep the big kernel semaphore locked, but we
+ * clear ->lock_depth so that schedule() doesnt
+ * auto-release the semaphore:
+ */
+#ifdef CONFIG_PREEMPT_BKL
+ saved_lock_depth = task->lock_depth;
+ task->lock_depth = -1;
+#endif
+ schedule();
+#ifdef CONFIG_PREEMPT_BKL
+ task->lock_depth = saved_lock_depth;
+#endif
+ sub_preempt_count(PREEMPT_ACTIVE);
+
+ /* we could miss a preemption opportunity between schedule and now */
+ barrier();
+ if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+ goto need_resched;
+}
+
+EXPORT_SYMBOL(preempt_schedule);
+
+/*
+ * this is is the entry point to schedule() from kernel preemption
+ * off of irq context.
+ * Note, that this is called and return with irqs disabled. This will
+ * protect us against recursive calling from irq.
+ */
+asmlinkage void __sched preempt_schedule_irq(void)
+{
+ struct thread_info *ti = current_thread_info();
+#ifdef CONFIG_PREEMPT_BKL
+ struct task_struct *task = current;
+ int saved_lock_depth;
+#endif
+ /* Catch callers which need to be fixed*/
+ BUG_ON(ti->preempt_count || !irqs_disabled());
+
+need_resched:
+ add_preempt_count(PREEMPT_ACTIVE);
+ /*
+ * We keep the big kernel semaphore locked, but we
+ * clear ->lock_depth so that schedule() doesnt
+ * auto-release the semaphore:
+ */
+#ifdef CONFIG_PREEMPT_BKL
+ saved_lock_depth = task->lock_depth;
+ task->lock_depth = -1;
+#endif
+ local_irq_enable();
+ schedule();
+ local_irq_disable();
+#ifdef CONFIG_PREEMPT_BKL
+ task->lock_depth = saved_lock_depth;
+#endif
+ sub_preempt_count(PREEMPT_ACTIVE);
+
+ /* we could miss a preemption opportunity between schedule and now */
+ barrier();
+ if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+ goto need_resched;
+}
+
+#endif /* CONFIG_PREEMPT */
+
+int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+ void *key)
+{
+ task_t *p = curr->private;
+ return try_to_wake_up(p, mode, sync);
+}
+
+EXPORT_SYMBOL(default_wake_function);
+
+/*
+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int sync, void *key)
+{
+ struct list_head *tmp, *next;
+
+ list_for_each_safe(tmp, next, &q->task_list) {
+ wait_queue_t *curr;
+ unsigned flags;
+ curr = list_entry(tmp, wait_queue_t, task_list);
+ flags = curr->flags;
+ if (curr->func(curr, mode, sync, key) &&
+ (flags & WQ_FLAG_EXCLUSIVE) &&
+ !--nr_exclusive)
+ break;
+ }
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ */
+void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, void *key)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->lock, flags);
+ __wake_up_common(q, mode, nr_exclusive, 0, key);
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+{
+ __wake_up_common(q, mode, 1, 0, NULL);
+}
+
+/**
+ * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ */
+void fastcall
+__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+ unsigned long flags;
+ int sync = 1;
+
+ if (unlikely(!q))
+ return;
+
+ if (unlikely(!nr_exclusive))
+ sync = 0;
+
+ spin_lock_irqsave(&q->lock, flags);
+ __wake_up_common(q, mode, nr_exclusive, sync, NULL);
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
+
+void fastcall complete(struct completion *x)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
x->done++;
__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
- 1, 0);
+ 1, 0, NULL);
+ spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+void fastcall complete_all(struct completion *x)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
+ x->done += UINT_MAX/2;
+ __wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
+ 0, 0, NULL);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
-EXPORT_SYMBOL(complete);
+EXPORT_SYMBOL(complete_all);
+
+void fastcall __sched wait_for_completion(struct completion *x)
+{
+ might_sleep();
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ wait.flags |= WQ_FLAG_EXCLUSIVE;
+ __add_wait_queue_tail(&x->wait, &wait);
+ do {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&x->wait.lock);
+ schedule();
+ spin_lock_irq(&x->wait.lock);
+ } while (!x->done);
+ __remove_wait_queue(&x->wait, &wait);
+ }
+ x->done--;
+ spin_unlock_irq(&x->wait.lock);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+unsigned long fastcall __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+ might_sleep();
+
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ wait.flags |= WQ_FLAG_EXCLUSIVE;
+ __add_wait_queue_tail(&x->wait, &wait);
+ do {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock_irq(&x->wait.lock);
+ timeout = schedule_timeout(timeout);
+ spin_lock_irq(&x->wait.lock);
+ if (!timeout) {
+ __remove_wait_queue(&x->wait, &wait);
+ goto out;
+ }
+ } while (!x->done);
+ __remove_wait_queue(&x->wait, &wait);
+ }
+ x->done--;
+out:
+ spin_unlock_irq(&x->wait.lock);
+ return timeout;
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+int fastcall __sched wait_for_completion_interruptible(struct completion *x)
+{
+ int ret = 0;
+
+ might_sleep();
+
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ wait.flags |= WQ_FLAG_EXCLUSIVE;
+ __add_wait_queue_tail(&x->wait, &wait);
+ do {
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ __remove_wait_queue(&x->wait, &wait);
+ goto out;
+ }
+ __set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_irq(&x->wait.lock);
+ schedule();
+ spin_lock_irq(&x->wait.lock);
+ } while (!x->done);
+ __remove_wait_queue(&x->wait, &wait);
+ }
+ x->done--;
+out:
+ spin_unlock_irq(&x->wait.lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+unsigned long fastcall __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+ unsigned long timeout)
+{
+ might_sleep();
+
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ wait.flags |= WQ_FLAG_EXCLUSIVE;
+ __add_wait_queue_tail(&x->wait, &wait);
+ do {
+ if (signal_pending(current)) {
+ timeout = -ERESTARTSYS;
+ __remove_wait_queue(&x->wait, &wait);
+ goto out;
+ }
+ __set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_irq(&x->wait.lock);
+ timeout = schedule_timeout(timeout);
+ spin_lock_irq(&x->wait.lock);
+ if (!timeout) {
+ __remove_wait_queue(&x->wait, &wait);
+ goto out;
+ }
+ } while (!x->done);
+ __remove_wait_queue(&x->wait, &wait);
+ }
+ x->done--;
+out:
+ spin_unlock_irq(&x->wait.lock);
+ return timeout;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+
+#define SLEEP_ON_VAR \
+ unsigned long flags; \
+ wait_queue_t wait; \
+ init_waitqueue_entry(&wait, current);
+
+#define SLEEP_ON_HEAD \
+ spin_lock_irqsave(&q->lock,flags); \
+ __add_wait_queue(q, &wait); \
+ spin_unlock(&q->lock);
+
+#define SLEEP_ON_TAIL \
+ spin_lock_irq(&q->lock); \
+ __remove_wait_queue(q, &wait); \
+ spin_unlock_irqrestore(&q->lock, flags);
+
+#define SLEEP_ON_BKLCHECK \
+ if (unlikely(!kernel_locked()) && \
+ sleep_on_bkl_warnings < 10) { \
+ sleep_on_bkl_warnings++; \
+ WARN_ON(1); \
+ }
+
+static int sleep_on_bkl_warnings;
+
+void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+ SLEEP_ON_VAR
+
+ SLEEP_ON_BKLCHECK
+
+ current->state = TASK_INTERRUPTIBLE;
+
+ SLEEP_ON_HEAD
+ schedule();
+ SLEEP_ON_TAIL
+}
+
+EXPORT_SYMBOL(interruptible_sleep_on);
+
+long fastcall __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+ SLEEP_ON_VAR
+
+ SLEEP_ON_BKLCHECK
+
+ current->state = TASK_INTERRUPTIBLE;
+
+ SLEEP_ON_HEAD
+ timeout = schedule_timeout(timeout);
+ SLEEP_ON_TAIL
+
+ return timeout;
+}
+
+EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+
+long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+ SLEEP_ON_VAR
+
+ SLEEP_ON_BKLCHECK
+
+ current->state = TASK_UNINTERRUPTIBLE;
+
+ SLEEP_ON_HEAD
+ timeout = schedule_timeout(timeout);
+ SLEEP_ON_TAIL
+
+ return timeout;
+}
+
+EXPORT_SYMBOL(sleep_on_timeout);
+
+void set_user_nice(task_t *p, long nice)
+{
+ unsigned long flags;
+ prio_array_t *array;
+ runqueue_t *rq;
+ int old_prio, new_prio, delta;
+
+ if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+ return;
+ /*
+ * We have to be careful, if called from sys_setpriority(),
+ * the task might be in the middle of scheduling on another CPU.
+ */
+ rq = task_rq_lock(p, &flags);
+ /*
+ * The RT priorities are set via sched_setscheduler(), but we still
+ * allow the 'normal' nice value to be set - but as expected
+ * it wont have any effect on scheduling until the task is
+ * not SCHED_NORMAL/SCHED_BATCH:
+ */
+ if (rt_task(p)) {
+ p->static_prio = NICE_TO_PRIO(nice);
+ goto out_unlock;
+ }
+ array = p->array;
+ if (array)
+ dequeue_task(p, array);
+
+ old_prio = p->prio;
+ new_prio = NICE_TO_PRIO(nice);
+ delta = new_prio - old_prio;
+ p->static_prio = NICE_TO_PRIO(nice);
+ p->prio += delta;
+
+ if (array) {
+ enqueue_task(p, array);
+ /*
+ * If the task increased its priority or is running and
+ * lowered its priority, then reschedule its CPU:
+ */
+ if (delta < 0 || (delta > 0 && task_running(rq, p)))
+ resched_task(rq->curr);
+ }
+out_unlock:
+ task_rq_unlock(rq, &flags);
+}
+
+EXPORT_SYMBOL(set_user_nice);
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const task_t *p, const int nice)
+{
+ /* convert nice value [19,-20] to rlimit style value [1,40] */
+ int nice_rlim = 20 - nice;
+ return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+ capable(CAP_SYS_NICE));
+}
+
+#ifdef __ARCH_WANT_SYS_NICE
+
+/*
+ * sys_nice - change the priority of the current process.
+ * @increment: priority increment
+ *
+ * sys_setpriority is a more generic, but much slower function that
+ * does similar things.
+ */
+asmlinkage long sys_nice(int increment)
+{
+ int retval;
+ long nice;
+
+ /*
+ * Setpriority might change our priority at the same moment.
+ * We don't have to worry. Conceptually one call occurs first
+ * and we have a single winner.
+ */
+ if (increment < -40)
+ increment = -40;
+ if (increment > 40)
+ increment = 40;
+
+ nice = PRIO_TO_NICE(current->static_prio) + increment;
+ if (nice < -20)
+ nice = -20;
+ if (nice > 19)
+ nice = 19;
+
+ if (increment < 0 && !can_nice(current, nice))
+ return vx_flags(VXF_IGNEG_NICE, 0) ? 0 : -EPERM;
+
+ retval = security_task_setnice(current, nice);
+ if (retval)
+ return retval;
+
+ set_user_nice(current, nice);
+ return 0;
+}
+
+#endif
+
+/**
+ * task_prio - return the priority value of a given task.
+ * @p: the task in question.
+ *
+ * This is the priority value as seen by users in /proc.
+ * RT tasks are offset by -200. Normal tasks are centered
+ * around 0, value goes from -16 to +15.
+ */
+int task_prio(const task_t *p)
+{
+ return p->prio - MAX_RT_PRIO;
+}
+
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ */
+int task_nice(const task_t *p)
+{
+ return TASK_NICE(p);
+}
+EXPORT_SYMBOL_GPL(task_nice);
+
+/**
+ * idle_cpu - is a given cpu idle currently?
+ * @cpu: the processor in question.
+ */
+int idle_cpu(int cpu)
+{
+ return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+}
+
+/**
+ * idle_task - return the idle task for a given cpu.
+ * @cpu: the processor in question.
+ */
+task_t *idle_task(int cpu)
+{
+ return cpu_rq(cpu)->idle;
+}
+
+/**
+ * find_process_by_pid - find a process with a matching PID value.
+ * @pid: the pid in question.
+ */
+static inline task_t *find_process_by_pid(pid_t pid)
+{
+ return pid ? find_task_by_pid(pid) : current;
+}
+
+/* Actually do priority change: must hold rq lock. */
+static void __setscheduler(struct task_struct *p, int policy, int prio)
+{
+ BUG_ON(p->array);
+ p->policy = policy;
+ p->rt_priority = prio;
+ if (policy != SCHED_NORMAL && policy != SCHED_BATCH) {
+ p->prio = MAX_RT_PRIO-1 - p->rt_priority;
+ } else {
+ p->prio = p->static_prio;
+ /*
+ * SCHED_BATCH tasks are treated as perpetual CPU hogs:
+ */
+ if (policy == SCHED_BATCH)
+ p->sleep_avg = 0;
+ }
+}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of
+ * a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+ struct sched_param *param)
+{
+ int retval;
+ int oldprio, oldpolicy = -1;
+ prio_array_t *array;
+ unsigned long flags;
+ runqueue_t *rq;
+
+recheck:
+ /* double check policy once rq lock held */
+ if (policy < 0)
+ policy = oldpolicy = p->policy;
+ else if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ policy != SCHED_NORMAL && policy != SCHED_BATCH)
+ return -EINVAL;
+ /*
+ * Valid priorities for SCHED_FIFO and SCHED_RR are
+ * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
+ * SCHED_BATCH is 0.
+ */
+ if (param->sched_priority < 0 ||
+ (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
+ (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+ return -EINVAL;
+ if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
+ != (param->sched_priority == 0))
+ return -EINVAL;
+
+ /*
+ * Allow unprivileged RT tasks to decrease priority:
+ */
+ if (!capable(CAP_SYS_NICE)) {
+ /*
+ * can't change policy, except between SCHED_NORMAL
+ * and SCHED_BATCH:
+ */
+ if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
+ (policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
+ !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
+ return -EPERM;
+ /* can't increase priority */
+ if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
+ param->sched_priority > p->rt_priority &&
+ param->sched_priority >
+ p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
+ return -EPERM;
+ /* can't change other user's priorities */
+ if ((current->euid != p->euid) &&
+ (current->euid != p->uid))
+ return -EPERM;
+ }
+
+ retval = security_task_setscheduler(p, policy, param);
+ if (retval)
+ return retval;
+ /*
+ * To be able to change p->policy safely, the apropriate
+ * runqueue lock must be held.
+ */
+ rq = task_rq_lock(p, &flags);
+ /* recheck policy now with rq lock held */
+ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+ policy = oldpolicy = -1;
+ task_rq_unlock(rq, &flags);
+ goto recheck;
+ }
+ array = p->array;
+ if (array)
+ deactivate_task(p, rq);
+ oldprio = p->prio;
+ __setscheduler(p, policy, param->sched_priority);
+ if (array) {
+ vx_activate_task(p);
+ __activate_task(p, rq);
+ /*
+ * Reschedule if we are currently running on this runqueue and
+ * our priority decreased, or if we are not currently running on
+ * this runqueue and our priority is higher than the current's
+ */
+ if (task_running(rq, p)) {
+ if (p->prio > oldprio)
+ resched_task(rq->curr);
+ } else if (TASK_PREEMPTS_CURR(p, rq))
+ resched_task(rq->curr);
+ }
+ task_rq_unlock(rq, &flags);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+{
+ int retval;
+ struct sched_param lparam;
+ struct task_struct *p;
+
+ if (!param || pid < 0)
+ return -EINVAL;
+ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
+ return -EFAULT;
+ read_lock_irq(&tasklist_lock);
+ p = find_process_by_pid(pid);
+ if (!p) {
+ read_unlock_irq(&tasklist_lock);
+ return -ESRCH;
+ }
+ retval = sched_setscheduler(p, policy, &lparam);
+ read_unlock_irq(&tasklist_lock);
+ return retval;
+}
+
+/**
+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
+ * @pid: the pid in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
+ struct sched_param __user *param)
+{
+ /* negative values for policy are not valid */
+ if (policy < 0)
+ return -EINVAL;
+
+ return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+{
+ return do_sched_setscheduler(pid, -1, param);
+}
+
+/**
+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
+ * @pid: the pid in question.
+ */
+asmlinkage long sys_sched_getscheduler(pid_t pid)
+{
+ int retval = -EINVAL;
+ task_t *p;
+
+ if (pid < 0)
+ goto out_nounlock;
+
+ retval = -ESRCH;
+ read_lock(&tasklist_lock);
+ p = find_process_by_pid(pid);
+ if (p) {
+ retval = security_task_getscheduler(p);
+ if (!retval)
+ retval = p->policy;
+ }
+ read_unlock(&tasklist_lock);
+
+out_nounlock:
+ return retval;
+}
+
+/**
+ * sys_sched_getscheduler - get the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the RT priority.
+ */
+asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+{
+ struct sched_param lp;
+ int retval = -EINVAL;
+ task_t *p;
+
+ if (!param || pid < 0)
+ goto out_nounlock;
+
+ read_lock(&tasklist_lock);
+ p = find_process_by_pid(pid);
+ retval = -ESRCH;
+ if (!p)
+ goto out_unlock;
+
+ retval = security_task_getscheduler(p);
+ if (retval)
+ goto out_unlock;
+
+ lp.sched_priority = p->rt_priority;
+ read_unlock(&tasklist_lock);
+
+ /*
+ * This one might sleep, we cannot do it with a spinlock held ...
+ */
+ retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+
+out_nounlock:
+ return retval;
+
+out_unlock:
+ read_unlock(&tasklist_lock);
+ return retval;
+}
+
+long sched_setaffinity(pid_t pid, cpumask_t new_mask)
+{
+ task_t *p;
+ int retval;
+ cpumask_t cpus_allowed;
+
+ lock_cpu_hotplug();
+ read_lock(&tasklist_lock);
+
+ p = find_process_by_pid(pid);
+ if (!p) {
+ read_unlock(&tasklist_lock);
+ unlock_cpu_hotplug();
+ return -ESRCH;
+ }
+
+ /*
+ * It is not safe to call set_cpus_allowed with the
+ * tasklist_lock held. We will bump the task_struct's
+ * usage count and then drop tasklist_lock.
+ */
+ get_task_struct(p);
+ read_unlock(&tasklist_lock);
+
+ retval = -EPERM;
+ if ((current->euid != p->euid) && (current->euid != p->uid) &&
+ !capable(CAP_SYS_NICE))
+ goto out_unlock;
+
+ cpus_allowed = cpuset_cpus_allowed(p);
+ cpus_and(new_mask, new_mask, cpus_allowed);
+ retval = set_cpus_allowed(p, new_mask);
+
+out_unlock:
+ put_task_struct(p);
+ unlock_cpu_hotplug();
+ return retval;
+}
+
+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
+ cpumask_t *new_mask)
+{
+ if (len < sizeof(cpumask_t)) {
+ memset(new_mask, 0, sizeof(cpumask_t));
+ } else if (len > sizeof(cpumask_t)) {
+ len = sizeof(cpumask_t);
+ }
+ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
+}
+
+/**
+ * sys_sched_setaffinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to the new cpu mask
+ */
+asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
+ unsigned long __user *user_mask_ptr)
+{
+ cpumask_t new_mask;
+ int retval;
+
+ retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
+ if (retval)
+ return retval;
+
+ return sched_setaffinity(pid, new_mask);
+}
+
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+
+cpumask_t cpu_present_map __read_mostly;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+#endif
+
+long sched_getaffinity(pid_t pid, cpumask_t *mask)
+{
+ int retval;
+ task_t *p;
+
+ lock_cpu_hotplug();
+ read_lock(&tasklist_lock);
+
+ retval = -ESRCH;
+ p = find_process_by_pid(pid);
+ if (!p)
+ goto out_unlock;
+
+ retval = 0;
+ cpus_and(*mask, p->cpus_allowed, cpu_online_map);
+
+out_unlock:
+ read_unlock(&tasklist_lock);
+ unlock_cpu_hotplug();
+ if (retval)
+ return retval;
+
+ return 0;
+}
+
+/**
+ * sys_sched_getaffinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ */
+asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
+ unsigned long __user *user_mask_ptr)
+{
+ int ret;
+ cpumask_t mask;
+
+ if (len < sizeof(cpumask_t))
+ return -EINVAL;
+
+ ret = sched_getaffinity(pid, &mask);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
+ return -EFAULT;
+
+ return sizeof(cpumask_t);
+}
+
+/**
+ * sys_sched_yield - yield the current processor to other threads.
+ *
+ * this function yields the current CPU by moving the calling thread
+ * to the expired array. If there are no other threads running on this
+ * CPU then this function will return.
+ */
+asmlinkage long sys_sched_yield(void)
+{
+ runqueue_t *rq = this_rq_lock();
+ prio_array_t *array = current->array;
+ prio_array_t *target = rq->expired;
+
+ schedstat_inc(rq, yld_cnt);
+ /*
+ * We implement yielding by moving the task into the expired
+ * queue.
+ *
+ * (special rule: RT tasks will just roundrobin in the active
+ * array.)
+ */
+ if (rt_task(current))
+ target = rq->active;
+
+ if (array->nr_active == 1) {
+ schedstat_inc(rq, yld_act_empty);
+ if (!rq->expired->nr_active)
+ schedstat_inc(rq, yld_both_empty);
+ } else if (!rq->expired->nr_active)
+ schedstat_inc(rq, yld_exp_empty);
+
+ if (array != target) {
+ dequeue_task(current, array);
+ enqueue_task(current, target);
+ } else
+ /*
+ * requeue_task is cheaper so perform that if possible.
+ */
+ requeue_task(current, array);
+
+ /*
+ * Since we are going to call schedule() anyway, there's
+ * no need to preempt or enable interrupts:
+ */
+ __release(rq->lock);
+ _raw_spin_unlock(&rq->lock);
+ preempt_enable_no_resched();
+
+ schedule();
+
+ return 0;
+}
+
+static inline void __cond_resched(void)
+{
+ /*
+ * The BKS might be reacquired before we have dropped
+ * PREEMPT_ACTIVE, which could trigger a second
+ * cond_resched() call.
+ */
+ if (unlikely(preempt_count()))
+ return;
+ if (unlikely(system_state != SYSTEM_RUNNING))
+ return;
+ do {
+ add_preempt_count(PREEMPT_ACTIVE);
+ schedule();
+ sub_preempt_count(PREEMPT_ACTIVE);
+ } while (need_resched());
+}
+
+int __sched cond_resched(void)
+{
+ if (need_resched()) {
+ __cond_resched();
+ return 1;
+ }
+ return 0;
+}
+
+EXPORT_SYMBOL(cond_resched);
+
+/*
+ * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * call schedule, and on return reacquire the lock.
+ *
+ * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * operations here to prevent schedule() from being called twice (once via
+ * spin_unlock(), once by hand).
+ */
+int cond_resched_lock(spinlock_t *lock)
+{
+ int ret = 0;
+
+ if (need_lockbreak(lock)) {
+ spin_unlock(lock);
+ cpu_relax();
+ ret = 1;
+ spin_lock(lock);
+ }
+ if (need_resched()) {
+ _raw_spin_unlock(lock);
+ preempt_enable_no_resched();
+ __cond_resched();
+ ret = 1;
+ spin_lock(lock);
+ }
+ return ret;
+}
+
+EXPORT_SYMBOL(cond_resched_lock);
+
+int __sched cond_resched_softirq(void)
+{
+ BUG_ON(!in_softirq());
+
+ if (need_resched()) {
+ __local_bh_enable();
+ __cond_resched();
+ local_bh_disable();
+ return 1;
+ }
+ return 0;
+}
+
+EXPORT_SYMBOL(cond_resched_softirq);
+
+
+/**
+ * yield - yield the current processor to other threads.
+ *
+ * this is a shortcut for kernel-space yielding - it marks the
+ * thread runnable and calls sys_sched_yield().
+ */
+void __sched yield(void)
+{
+ set_current_state(TASK_RUNNING);
+ sys_sched_yield();
+}
+
+EXPORT_SYMBOL(yield);
+
+/*
+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
+ * that process accounting knows that this is a task in IO wait state.
+ *
+ * But don't do that if it is a deliberate, throttling IO wait (this task
+ * has set its backing_dev_info: the queue against which it should throttle)
+ */
+void __sched io_schedule(void)
+{
+ struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+
+ atomic_inc(&rq->nr_iowait);
+ schedule();
+ atomic_dec(&rq->nr_iowait);
+}
+
+EXPORT_SYMBOL(io_schedule);
+
+long __sched io_schedule_timeout(long timeout)
+{
+ struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+ long ret;
+
+ atomic_inc(&rq->nr_iowait);
+ ret = schedule_timeout(timeout);
+ atomic_dec(&rq->nr_iowait);
+ return ret;
+}
+
+/**
+ * sys_sched_get_priority_max - return maximum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the maximum rt_priority that can be used
+ * by a given scheduling class.
+ */
+asmlinkage long sys_sched_get_priority_max(int policy)
+{
+ int ret = -EINVAL;
+
+ switch (policy) {
+ case SCHED_FIFO:
+ case SCHED_RR:
+ ret = MAX_USER_RT_PRIO-1;
+ break;
+ case SCHED_NORMAL:
+ case SCHED_BATCH:
+ ret = 0;
+ break;
+ }
+ return ret;
+}
+
+/**
+ * sys_sched_get_priority_min - return minimum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the minimum rt_priority that can be used
+ * by a given scheduling class.
+ */
+asmlinkage long sys_sched_get_priority_min(int policy)
+{
+ int ret = -EINVAL;
+
+ switch (policy) {
+ case SCHED_FIFO:
+ case SCHED_RR:
+ ret = 1;
+ break;
+ case SCHED_NORMAL:
+ case SCHED_BATCH:
+ ret = 0;
+ }
+ return ret;
+}
+
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ */
+asmlinkage
+long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+{
+ int retval = -EINVAL;
+ struct timespec t;
+ task_t *p;
+
+ if (pid < 0)
+ goto out_nounlock;
+
+ retval = -ESRCH;
+ read_lock(&tasklist_lock);
+ p = find_process_by_pid(pid);
+ if (!p)
+ goto out_unlock;
+
+ retval = security_task_getscheduler(p);
+ if (retval)
+ goto out_unlock;
+
+ jiffies_to_timespec(p->policy & SCHED_FIFO ?
+ 0 : task_timeslice(p), &t);
+ read_unlock(&tasklist_lock);
+ retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+out_nounlock:
+ return retval;
+out_unlock:
+ read_unlock(&tasklist_lock);
+ return retval;
+}
+
+static inline struct task_struct *eldest_child(struct task_struct *p)
+{
+ if (list_empty(&p->children)) return NULL;
+ return list_entry(p->children.next,struct task_struct,sibling);
+}
+
+static inline struct task_struct *older_sibling(struct task_struct *p)
+{
+ if (p->sibling.prev==&p->parent->children) return NULL;
+ return list_entry(p->sibling.prev,struct task_struct,sibling);
+}
+
+static inline struct task_struct *younger_sibling(struct task_struct *p)
+{
+ if (p->sibling.next==&p->parent->children) return NULL;
+ return list_entry(p->sibling.next,struct task_struct,sibling);
+}
+
+static void show_task(task_t *p)
+{
+ task_t *relative;
+ unsigned state;
+ unsigned long free = 0;
+ static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };
+
+ printk("%-13.13s ", p->comm);
+ state = p->state ? __ffs(p->state) + 1 : 0;
+ if (state < ARRAY_SIZE(stat_nam))
+ printk(stat_nam[state]);
+ else
+ printk("?");
+#if (BITS_PER_LONG == 32)
+ if (state == TASK_RUNNING)
+ printk(" running ");
+ else
+ printk(" %08lX ", thread_saved_pc(p));
+#else
+ if (state == TASK_RUNNING)
+ printk(" running task ");
+ else
+ printk(" %016lx ", thread_saved_pc(p));
+#endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+ {
+ unsigned long *n = end_of_stack(p);
+ while (!*n)
+ n++;
+ free = (unsigned long)n - (unsigned long)end_of_stack(p);
+ }
+#endif
+ printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
+ if ((relative = eldest_child(p)))
+ printk("%5d ", relative->pid);
+ else
+ printk(" ");
+ if ((relative = younger_sibling(p)))
+ printk("%7d", relative->pid);
+ else
+ printk(" ");
+ if ((relative = older_sibling(p)))
+ printk(" %5d", relative->pid);
+ else
+ printk(" ");
+ if (!p->mm)
+ printk(" (L-TLB)\n");
+ else
+ printk(" (NOTLB)\n");
+
+ if (state != TASK_RUNNING)
+ show_stack(p, NULL);
+}
+
+void show_state(void)
+{
+ task_t *g, *p;
+
+#if (BITS_PER_LONG == 32)
+ printk("\n"
+ " sibling\n");
+ printk(" task PC pid father child younger older\n");
+#else
+ printk("\n"
+ " sibling\n");
+ printk(" task PC pid father child younger older\n");
+#endif
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ /*
+ * reset the NMI-timeout, listing all files on a slow
+ * console might take alot of time:
+ */
+ touch_nmi_watchdog();
+ show_task(p);
+ } while_each_thread(g, p);
+
+ read_unlock(&tasklist_lock);
+ mutex_debug_show_all_locks();
+}
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void __devinit init_idle(task_t *idle, int cpu)
+{
+ runqueue_t *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ idle->timestamp = sched_clock();
+ idle->sleep_avg = 0;
+ idle->array = NULL;
+ idle->prio = MAX_PRIO;
+ idle->state = TASK_RUNNING;
+ idle->cpus_allowed = cpumask_of_cpu(cpu);
+ set_task_cpu(idle, cpu);
+
+ spin_lock_irqsave(&rq->lock, flags);
+ rq->curr = rq->idle = idle;
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ idle->oncpu = 1;
+#endif
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ /* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
+ task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
+ task_thread_info(idle)->preempt_count = 0;
+#endif
+}
+
+/*
+ * In a system that switches off the HZ timer nohz_cpu_mask
+ * indicates which cpus entered this state. This is used
+ * in the rcu update to wait only for active cpus. For system
+ * which do not switch off the HZ timer nohz_cpu_mask should
+ * always be CPU_MASK_NONE.
+ */
+cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+
+#ifdef CONFIG_SMP
+/*
+ * This is how migration works:
+ *
+ * 1) we queue a migration_req_t structure in the source CPU's
+ * runqueue and wake up that CPU's migration thread.
+ * 2) we down() the locked semaphore => thread blocks.
+ * 3) migration thread wakes up (implicitly it forces the migrated
+ * thread off the CPU)
+ * 4) it gets the migration request and checks whether the migrated
+ * task is still in the wrong runqueue.
+ * 5) if it's in the wrong runqueue then the migration thread removes
+ * it and puts it into the right queue.
+ * 6) migration thread up()s the semaphore.
+ * 7) we wake up and the migration is done.
+ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+{
+ unsigned long flags;
+ int ret = 0;
+ migration_req_t req;
+ runqueue_t *rq;
+
+ rq = task_rq_lock(p, &flags);
+ if (!cpus_intersects(new_mask, cpu_online_map)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ p->cpus_allowed = new_mask;
+ /* Can the task run on the task's current CPU? If so, we're done */
+ if (cpu_isset(task_cpu(p), new_mask))
+ goto out;
+
+ if (migrate_task(p, any_online_cpu(new_mask), &req)) {
+ /* Need help from migration thread: drop lock and wait. */
+ task_rq_unlock(rq, &flags);
+ wake_up_process(rq->migration_thread);
+ wait_for_completion(&req.done);
+ tlb_migrate_finish(p->mm);
+ return 0;
+ }
+out:
+ task_rq_unlock(rq, &flags);
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(set_cpus_allowed);
+
+/*
+ * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * this because either it can't run here any more (set_cpus_allowed()
+ * away from this CPU, or CPU going down), or because we're
+ * attempting to rebalance this task on exec (sched_exec).
+ *
+ * So we race with normal scheduler movements, but that's OK, as long
+ * as the task is no longer on this CPU.
+ */
+static void __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+ runqueue_t *rq_dest, *rq_src;
+
+ if (unlikely(cpu_is_offline(dest_cpu)))
+ return;
+
+ rq_src = cpu_rq(src_cpu);
+ rq_dest = cpu_rq(dest_cpu);
+
+ double_rq_lock(rq_src, rq_dest);
+ /* Already moved. */
+ if (task_cpu(p) != src_cpu)
+ goto out;
+ /* Affinity changed (again). */
+ if (!cpu_isset(dest_cpu, p->cpus_allowed))
+ goto out;
+
+ set_task_cpu(p, dest_cpu);
+ if (p->array) {
+ /*
+ * Sync timestamp with rq_dest's before activating.
+ * The same thing could be achieved by doing this step
+ * afterwards, and pretending it was a local activate.
+ * This way is cleaner and logically correct.
+ */
+ p->timestamp = p->timestamp - rq_src->timestamp_last_tick
+ + rq_dest->timestamp_last_tick;
+ deactivate_task(p, rq_src);
+ activate_task(p, rq_dest, 0);
+ if (TASK_PREEMPTS_CURR(p, rq_dest))
+ resched_task(rq_dest->curr);
+ }
+
+out:
+ double_rq_unlock(rq_src, rq_dest);
+}
+
+/*
+ * migration_thread - this is a highprio system thread that performs
+ * thread migration by bumping thread off CPU then 'pushing' onto
+ * another runqueue.
+ */
+static int migration_thread(void *data)
+{
+ runqueue_t *rq;
+ int cpu = (long)data;
+
+ rq = cpu_rq(cpu);
+ BUG_ON(rq->migration_thread != current);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ struct list_head *head;
+ migration_req_t *req;
+
+ try_to_freeze();
+
+ spin_lock_irq(&rq->lock);
+
+ if (cpu_is_offline(cpu)) {
+ spin_unlock_irq(&rq->lock);
+ goto wait_to_die;
+ }
+
+ if (rq->active_balance) {
+ active_load_balance(rq, cpu);
+ rq->active_balance = 0;
+ }
+
+ head = &rq->migration_queue;
+
+ if (list_empty(head)) {
+ spin_unlock_irq(&rq->lock);
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ continue;
+ }
+ req = list_entry(head->next, migration_req_t, list);
+ list_del_init(head->next);
+
+ spin_unlock(&rq->lock);
+ __migrate_task(req->task, cpu, req->dest_cpu);
+ local_irq_enable();
+
+ complete(&req->done);
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+
+wait_to_die:
+ /* Wait for kthread_stop */
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* Figure out where task on dead CPU should go, use force if neccessary. */
+static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
+{
+ int dest_cpu;
+ cpumask_t mask;
+
+ /* On same node? */
+ mask = node_to_cpumask(cpu_to_node(dead_cpu));
+ cpus_and(mask, mask, tsk->cpus_allowed);
+ dest_cpu = any_online_cpu(mask);
+
+ /* On any allowed CPU? */
+ if (dest_cpu == NR_CPUS)
+ dest_cpu = any_online_cpu(tsk->cpus_allowed);
+
+ /* No more Mr. Nice Guy. */
+ if (dest_cpu == NR_CPUS) {
+ cpus_setall(tsk->cpus_allowed);
+ dest_cpu = any_online_cpu(tsk->cpus_allowed);
+
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (tsk->mm && printk_ratelimit())
+ printk(KERN_INFO "process %d (%s) no "
+ "longer affine to cpu%d\n",
+ tsk->pid, tsk->comm, dead_cpu);
+ }
+ __migrate_task(tsk, dead_cpu, dest_cpu);
+}
+
+/*
+ * While a dead CPU has no uninterruptible tasks queued at this point,
+ * it might still have a nonzero ->nr_uninterruptible counter, because
+ * for performance reasons the counter is not stricly tracking tasks to
+ * their home CPUs. So we just add the counter to another CPU's counter,
+ * to keep the global sum constant after CPU-down:
+ */
+static void migrate_nr_uninterruptible(runqueue_t *rq_src)
+{
+ runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
+ unsigned long flags;
+
+ local_irq_save(flags);
+ double_rq_lock(rq_src, rq_dest);
+ rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
+ rq_src->nr_uninterruptible = 0;
+ double_rq_unlock(rq_src, rq_dest);
+ local_irq_restore(flags);
+}
+
+/* Run through task list and migrate tasks from the dead cpu. */
+static void migrate_live_tasks(int src_cpu)
+{
+ struct task_struct *tsk, *t;
+
+ write_lock_irq(&tasklist_lock);
+
+ do_each_thread(t, tsk) {
+ if (tsk == current)
+ continue;
+
+ if (task_cpu(tsk) == src_cpu)
+ move_task_off_dead_cpu(src_cpu, tsk);
+ } while_each_thread(t, tsk);
+
+ write_unlock_irq(&tasklist_lock);
+}
+
+/* Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible and adding it to
+ * the _front_ of runqueue. Used by CPU offline code.
+ */
+void sched_idle_next(void)
+{
+ int cpu = smp_processor_id();
+ runqueue_t *rq = this_rq();
+ struct task_struct *p = rq->idle;
+ unsigned long flags;
+
+ /* cpu has to be offline */
+ BUG_ON(cpu_online(cpu));
+
+ /* Strictly not necessary since rest of the CPUs are stopped by now
+ * and interrupts disabled on current cpu.
+ */
+ spin_lock_irqsave(&rq->lock, flags);
+
+ __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+ /* Add idle task to _front_ of it's priority queue */
+ __activate_idle_task(p, rq);
+
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+/* Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+ struct mm_struct *mm = current->active_mm;
+
+ BUG_ON(cpu_online(smp_processor_id()));
+
+ if (mm != &init_mm)
+ switch_mm(mm, &init_mm, current);
+ mmdrop(mm);
+}
+
+static void migrate_dead(unsigned int dead_cpu, task_t *tsk)
+{
+ struct runqueue *rq = cpu_rq(dead_cpu);
+
+ /* Must be exiting, otherwise would be on tasklist. */
+ BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD);
+
+ /* Cannot have done final schedule yet: would have vanished. */
+ BUG_ON(tsk->flags & PF_DEAD);
+
+ get_task_struct(tsk);
+
+ /*
+ * Drop lock around migration; if someone else moves it,
+ * that's OK. No task can be added to this CPU, so iteration is
+ * fine.
+ */
+ spin_unlock_irq(&rq->lock);
+ move_task_off_dead_cpu(dead_cpu, tsk);
+ spin_lock_irq(&rq->lock);
+
+ put_task_struct(tsk);
+}
+
+/* release_task() removes task from tasklist, so we won't find dead tasks. */
+static void migrate_dead_tasks(unsigned int dead_cpu)
+{
+ unsigned arr, i;
+ struct runqueue *rq = cpu_rq(dead_cpu);
+
+ for (arr = 0; arr < 2; arr++) {
+ for (i = 0; i < MAX_PRIO; i++) {
+ struct list_head *list = &rq->arrays[arr].queue[i];
+ while (!list_empty(list))
+ migrate_dead(dead_cpu,
+ list_entry(list->next, task_t,
+ run_list));
+ }
+ }
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+static int migration_call(struct notifier_block *nfb, unsigned long action,
+ void *hcpu)
+{
+ int cpu = (long)hcpu;
+ struct task_struct *p;
+ struct runqueue *rq;
+ unsigned long flags;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
+ if (IS_ERR(p))
+ return NOTIFY_BAD;
+ p->flags |= PF_NOFREEZE;
+ kthread_bind(p, cpu);
+ /* Must be high prio: stop_machine expects to yield to it. */
+ rq = task_rq_lock(p, &flags);
+ __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+ task_rq_unlock(rq, &flags);
+ cpu_rq(cpu)->migration_thread = p;
+ break;
+ case CPU_ONLINE:
+ /* Strictly unneccessary, as first user will wake it. */
+ wake_up_process(cpu_rq(cpu)->migration_thread);
+ break;
+#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_UP_CANCELED:
+ /* Unbind it from offline cpu so it can run. Fall thru. */
+ kthread_bind(cpu_rq(cpu)->migration_thread,
+ any_online_cpu(cpu_online_map));
+ kthread_stop(cpu_rq(cpu)->migration_thread);
+ cpu_rq(cpu)->migration_thread = NULL;
+ break;
+ case CPU_DEAD:
+ migrate_live_tasks(cpu);
+ rq = cpu_rq(cpu);
+ kthread_stop(rq->migration_thread);
+ rq->migration_thread = NULL;
+ /* Idle task back to normal (off runqueue, low prio) */
+ rq = task_rq_lock(rq->idle, &flags);
+ deactivate_task(rq->idle, rq);
+ rq->idle->static_prio = MAX_PRIO;
+ __setscheduler(rq->idle, SCHED_NORMAL, 0);
+ migrate_dead_tasks(cpu);
+ task_rq_unlock(rq, &flags);
+ migrate_nr_uninterruptible(rq);
+ BUG_ON(rq->nr_running != 0);
+
+ /* No need to migrate the tasks: it was best-effort if
+ * they didn't do lock_cpu_hotplug(). Just wake up
+ * the requestors. */
+ spin_lock_irq(&rq->lock);
+ while (!list_empty(&rq->migration_queue)) {
+ migration_req_t *req;
+ req = list_entry(rq->migration_queue.next,
+ migration_req_t, list);
+ list_del_init(&req->list);
+ complete(&req->done);
+ }
+ spin_unlock_irq(&rq->lock);
+ break;
+#endif
+ }
+ return NOTIFY_OK;
+}
-void fastcall complete_all(struct completion *x)
-{
- unsigned long flags;
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block migration_notifier = {
+ .notifier_call = migration_call,
+ .priority = 10
+};
- spin_lock_irqsave(&x->wait.lock, flags);
- x->done += UINT_MAX/2;
- __wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
- 0, 0);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+int __init migration_init(void)
+{
+ void *cpu = (void *)(long)smp_processor_id();
+ /* Start one for boot CPU. */
+ migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ migration_call(&migration_notifier, CPU_ONLINE, cpu);
+ register_cpu_notifier(&migration_notifier);
+ return 0;
}
-EXPORT_SYMBOL(complete_all);
+#endif
-void fastcall __sched wait_for_completion(struct completion *x)
+#ifdef CONFIG_SMP
+#undef SCHED_DOMAIN_DEBUG
+#ifdef SCHED_DOMAIN_DEBUG
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
- might_sleep();
- spin_lock_irq(&x->wait.lock);
- if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
+ int level = 0;
- wait.flags |= WQ_FLAG_EXCLUSIVE;
- __add_wait_queue_tail(&x->wait, &wait);
- do {
- __set_current_state(TASK_UNINTERRUPTIBLE);
- spin_unlock_irq(&x->wait.lock);
- schedule();
- spin_lock_irq(&x->wait.lock);
- } while (!x->done);
- __remove_wait_queue(&x->wait, &wait);
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
}
- x->done--;
- spin_unlock_irq(&x->wait.lock);
-}
-EXPORT_SYMBOL(wait_for_completion);
-#define SLEEP_ON_VAR \
- unsigned long flags; \
- wait_queue_t wait; \
- init_waitqueue_entry(&wait, current);
+ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
-#define SLEEP_ON_HEAD \
- spin_lock_irqsave(&q->lock,flags); \
- __add_wait_queue(q, &wait); \
- spin_unlock(&q->lock);
+ do {
+ int i;
+ char str[NR_CPUS];
+ struct sched_group *group = sd->groups;
+ cpumask_t groupmask;
+
+ cpumask_scnprintf(str, NR_CPUS, sd->span);
+ cpus_clear(groupmask);
+
+ printk(KERN_DEBUG);
+ for (i = 0; i < level + 1; i++)
+ printk(" ");
+ printk("domain %d: ", level);
+
+ if (!(sd->flags & SD_LOAD_BALANCE)) {
+ printk("does not load-balance\n");
+ if (sd->parent)
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
+ break;
+ }
-#define SLEEP_ON_TAIL \
- spin_lock_irq(&q->lock); \
- __remove_wait_queue(q, &wait); \
- spin_unlock_irqrestore(&q->lock, flags);
+ printk("span %s\n", str);
-void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
-{
- SLEEP_ON_VAR
+ if (!cpu_isset(cpu, sd->span))
+ printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
+ if (!cpu_isset(cpu, group->cpumask))
+ printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
- current->state = TASK_INTERRUPTIBLE;
+ printk(KERN_DEBUG);
+ for (i = 0; i < level + 2; i++)
+ printk(" ");
+ printk("groups:");
+ do {
+ if (!group) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: group is NULL\n");
+ break;
+ }
- SLEEP_ON_HEAD
- schedule();
- SLEEP_ON_TAIL
-}
+ if (!group->cpu_power) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: domain->cpu_power not set\n");
+ }
-EXPORT_SYMBOL(interruptible_sleep_on);
+ if (!cpus_weight(group->cpumask)) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: empty group\n");
+ }
-long fastcall __sched interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
- SLEEP_ON_VAR
+ if (cpus_intersects(groupmask, group->cpumask)) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: repeated CPUs\n");
+ }
- current->state = TASK_INTERRUPTIBLE;
+ cpus_or(groupmask, groupmask, group->cpumask);
- SLEEP_ON_HEAD
- timeout = schedule_timeout(timeout);
- SLEEP_ON_TAIL
+ cpumask_scnprintf(str, NR_CPUS, group->cpumask);
+ printk(" %s", str);
- return timeout;
-}
+ group = group->next;
+ } while (group != sd->groups);
+ printk("\n");
-EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+ if (!cpus_equal(sd->span, groupmask))
+ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
-void fastcall __sched sleep_on(wait_queue_head_t *q)
-{
- SLEEP_ON_VAR
+ level++;
+ sd = sd->parent;
- current->state = TASK_UNINTERRUPTIBLE;
+ if (sd) {
+ if (!cpus_subset(groupmask, sd->span))
+ printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
+ }
- SLEEP_ON_HEAD
- schedule();
- SLEEP_ON_TAIL
+ } while (sd);
}
+#else
+#define sched_domain_debug(sd, cpu) {}
+#endif
-EXPORT_SYMBOL(sleep_on);
-
-long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+static int sd_degenerate(struct sched_domain *sd)
{
- SLEEP_ON_VAR
-
- current->state = TASK_UNINTERRUPTIBLE;
+ if (cpus_weight(sd->span) == 1)
+ return 1;
+
+ /* Following flags need at least 2 groups */
+ if (sd->flags & (SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC)) {
+ if (sd->groups != sd->groups->next)
+ return 0;
+ }
- SLEEP_ON_HEAD
- timeout = schedule_timeout(timeout);
- SLEEP_ON_TAIL
+ /* Following flags don't use groups */
+ if (sd->flags & (SD_WAKE_IDLE |
+ SD_WAKE_AFFINE |
+ SD_WAKE_BALANCE))
+ return 0;
- return timeout;
+ return 1;
}
-EXPORT_SYMBOL(sleep_on_timeout);
-
-void set_user_nice(task_t *p, long nice)
+static int sd_parent_degenerate(struct sched_domain *sd,
+ struct sched_domain *parent)
{
- unsigned long flags;
- prio_array_t *array;
- runqueue_t *rq;
- int old_prio, new_prio, delta;
+ unsigned long cflags = sd->flags, pflags = parent->flags;
- if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
- return;
- /*
- * We have to be careful, if called from sys_setpriority(),
- * the task might be in the middle of scheduling on another CPU.
- */
- rq = task_rq_lock(p, &flags);
- /*
- * The RT priorities are set via setscheduler(), but we still
- * allow the 'normal' nice value to be set - but as expected
- * it wont have any effect on scheduling until the task is
- * not SCHED_NORMAL:
- */
- if (rt_task(p)) {
- p->static_prio = NICE_TO_PRIO(nice);
- goto out_unlock;
- }
- array = p->array;
- if (array)
- dequeue_task(p, array);
+ if (sd_degenerate(parent))
+ return 1;
- old_prio = p->prio;
- new_prio = NICE_TO_PRIO(nice);
- delta = new_prio - old_prio;
- p->static_prio = NICE_TO_PRIO(nice);
- p->prio += delta;
+ if (!cpus_equal(sd->span, parent->span))
+ return 0;
- if (array) {
- enqueue_task(p, array);
- /*
- * If the task increased its priority or is running and
- * lowered its priority, then reschedule its CPU:
- */
- if (delta < 0 || (delta > 0 && task_running(rq, p)))
- resched_task(rq->curr);
+ /* Does parent contain flags not in child? */
+ /* WAKE_BALANCE is a subset of WAKE_AFFINE */
+ if (cflags & SD_WAKE_AFFINE)
+ pflags &= ~SD_WAKE_BALANCE;
+ /* Flags needing groups don't count if only 1 group in parent */
+ if (parent->groups == parent->groups->next) {
+ pflags &= ~(SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC);
}
-out_unlock:
- task_rq_unlock(rq, &flags);
-}
-
-EXPORT_SYMBOL(set_user_nice);
+ if (~cflags & pflags)
+ return 0;
-#ifndef __alpha__
+ return 1;
+}
/*
- * sys_nice - change the priority of the current process.
- * @increment: priority increment
- *
- * sys_setpriority is a more generic, but much slower function that
- * does similar things.
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
*/
-asmlinkage long sys_nice(int increment)
+static void cpu_attach_domain(struct sched_domain *sd, int cpu)
{
- int retval;
- long nice;
+ runqueue_t *rq = cpu_rq(cpu);
+ struct sched_domain *tmp;
- /*
- * Setpriority might change our priority at the same moment.
- * We don't have to worry. Conceptually one call occurs first
- * and we have a single winner.
- */
- if (increment < 0) {
- if (!capable(CAP_SYS_NICE))
- return -EPERM;
- if (increment < -40)
- increment = -40;
+ /* Remove the sched domains which do not contribute to scheduling. */
+ for (tmp = sd; tmp; tmp = tmp->parent) {
+ struct sched_domain *parent = tmp->parent;
+ if (!parent)
+ break;
+ if (sd_parent_degenerate(tmp, parent))
+ tmp->parent = parent->parent;
}
- if (increment > 40)
- increment = 40;
- nice = PRIO_TO_NICE(current->static_prio) + increment;
- if (nice < -20)
- nice = -20;
- if (nice > 19)
- nice = 19;
+ if (sd && sd_degenerate(sd))
+ sd = sd->parent;
- retval = security_task_setnice(current, nice);
- if (retval)
- return retval;
+ sched_domain_debug(sd, cpu);
- set_user_nice(current, nice);
- return 0;
+ rcu_assign_pointer(rq->sd, sd);
}
-#endif
+/* cpus with isolated domains */
+static cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;
-/**
- * task_prio - return the priority value of a given task.
- * @p: the task in question.
- *
- * This is the priority value as seen by users in /proc.
- * RT tasks are offset by -200. Normal tasks are centered
- * around 0, value goes from -16 to +15.
- */
-int task_prio(task_t *p)
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
{
- return p->prio - MAX_RT_PRIO;
-}
+ int ints[NR_CPUS], i;
-/**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- */
-int task_nice(task_t *p)
-{
- return TASK_NICE(p);
+ str = get_options(str, ARRAY_SIZE(ints), ints);
+ cpus_clear(cpu_isolated_map);
+ for (i = 1; i <= ints[0]; i++)
+ if (ints[i] < NR_CPUS)
+ cpu_set(ints[i], cpu_isolated_map);
+ return 1;
}
-EXPORT_SYMBOL(task_nice);
+__setup ("isolcpus=", isolated_cpu_setup);
-/**
- * idle_cpu - is a given cpu idle currently?
- * @cpu: the processor in question.
+/*
+ * init_sched_build_groups takes an array of groups, the cpumask we wish
+ * to span, and a pointer to a function which identifies what group a CPU
+ * belongs to. The return value of group_fn must be a valid index into the
+ * groups[] array, and must be >= 0 and < NR_CPUS (due to the fact that we
+ * keep track of groups covered with a cpumask_t).
+ *
+ * init_sched_build_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
*/
-int idle_cpu(int cpu)
+static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
+ int (*group_fn)(int cpu))
{
- return cpu_curr(cpu) == cpu_rq(cpu)->idle;
-}
+ struct sched_group *first = NULL, *last = NULL;
+ cpumask_t covered = CPU_MASK_NONE;
+ int i;
-EXPORT_SYMBOL_GPL(idle_cpu);
+ for_each_cpu_mask(i, span) {
+ int group = group_fn(i);
+ struct sched_group *sg = &groups[group];
+ int j;
-/**
- * find_process_by_pid - find a process with a matching PID value.
- * @pid: the pid in question.
- */
-static inline task_t *find_process_by_pid(pid_t pid)
-{
- return pid ? find_task_by_pid(pid) : current;
-}
+ if (cpu_isset(i, covered))
+ continue;
-/* Actually do priority change: must hold rq lock. */
-static void __setscheduler(struct task_struct *p, int policy, int prio)
-{
- BUG_ON(p->array);
- p->policy = policy;
- p->rt_priority = prio;
- if (policy != SCHED_NORMAL)
- p->prio = MAX_USER_RT_PRIO-1 - p->rt_priority;
- else
- p->prio = p->static_prio;
+ sg->cpumask = CPU_MASK_NONE;
+ sg->cpu_power = 0;
+
+ for_each_cpu_mask(j, span) {
+ if (group_fn(j) != group)
+ continue;
+
+ cpu_set(j, covered);
+ cpu_set(j, sg->cpumask);
+ }
+ if (!first)
+ first = sg;
+ if (last)
+ last->next = sg;
+ last = sg;
+ }
+ last->next = first;
}
+#define SD_NODES_PER_DOMAIN 16
+
/*
- * setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * Self-tuning task migration cost measurement between source and target CPUs.
+ *
+ * This is done by measuring the cost of manipulating buffers of varying
+ * sizes. For a given buffer-size here are the steps that are taken:
+ *
+ * 1) the source CPU reads+dirties a shared buffer
+ * 2) the target CPU reads+dirties the same shared buffer
+ *
+ * We measure how long they take, in the following 4 scenarios:
+ *
+ * - source: CPU1, target: CPU2 | cost1
+ * - source: CPU2, target: CPU1 | cost2
+ * - source: CPU1, target: CPU1 | cost3
+ * - source: CPU2, target: CPU2 | cost4
+ *
+ * We then calculate the cost3+cost4-cost1-cost2 difference - this is
+ * the cost of migration.
+ *
+ * We then start off from a small buffer-size and iterate up to larger
+ * buffer sizes, in 5% steps - measuring each buffer-size separately, and
+ * doing a maximum search for the cost. (The maximum cost for a migration
+ * normally occurs when the working set size is around the effective cache
+ * size.)
*/
-static int setscheduler(pid_t pid, int policy, struct sched_param __user *param)
-{
- struct sched_param lp;
- int retval = -EINVAL;
- int oldprio;
- prio_array_t *array;
- unsigned long flags;
- runqueue_t *rq;
- task_t *p;
-
- if (!param || pid < 0)
- goto out_nounlock;
-
- retval = -EFAULT;
- if (copy_from_user(&lp, param, sizeof(struct sched_param)))
- goto out_nounlock;
+#define SEARCH_SCOPE 2
+#define MIN_CACHE_SIZE (64*1024U)
+#define DEFAULT_CACHE_SIZE (5*1024*1024U)
+#define ITERATIONS 1
+#define SIZE_THRESH 130
+#define COST_THRESH 130
- /*
- * We play safe to avoid deadlocks.
- */
- read_lock_irq(&tasklist_lock);
+/*
+ * The migration cost is a function of 'domain distance'. Domain
+ * distance is the number of steps a CPU has to iterate down its
+ * domain tree to share a domain with the other CPU. The farther
+ * two CPUs are from each other, the larger the distance gets.
+ *
+ * Note that we use the distance only to cache measurement results,
+ * the distance value is not used numerically otherwise. When two
+ * CPUs have the same distance it is assumed that the migration
+ * cost is the same. (this is a simplification but quite practical)
+ */
+#define MAX_DOMAIN_DISTANCE 32
- p = find_process_by_pid(pid);
+static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
+ { [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
+/*
+ * Architectures may override the migration cost and thus avoid
+ * boot-time calibration. Unit is nanoseconds. Mostly useful for
+ * virtualized hardware:
+ */
+#ifdef CONFIG_DEFAULT_MIGRATION_COST
+ CONFIG_DEFAULT_MIGRATION_COST
+#else
+ -1LL
+#endif
+};
- retval = -ESRCH;
- if (!p)
- goto out_unlock_tasklist;
+/*
+ * Allow override of migration cost - in units of microseconds.
+ * E.g. migration_cost=1000,2000,3000 will set up a level-1 cost
+ * of 1 msec, level-2 cost of 2 msecs and level3 cost of 3 msecs:
+ */
+static int __init migration_cost_setup(char *str)
+{
+ int ints[MAX_DOMAIN_DISTANCE+1], i;
- /*
- * To be able to change p->policy safely, the apropriate
- * runqueue lock must be held.
- */
- rq = task_rq_lock(p, &flags);
+ str = get_options(str, ARRAY_SIZE(ints), ints);
- if (policy < 0)
- policy = p->policy;
- else {
- retval = -EINVAL;
- if (policy != SCHED_FIFO && policy != SCHED_RR &&
- policy != SCHED_NORMAL)
- goto out_unlock;
+ printk("#ints: %d\n", ints[0]);
+ for (i = 1; i <= ints[0]; i++) {
+ migration_cost[i-1] = (unsigned long long)ints[i]*1000;
+ printk("migration_cost[%d]: %Ld\n", i-1, migration_cost[i-1]);
}
+ return 1;
+}
- /*
- * Valid priorities for SCHED_FIFO and SCHED_RR are
- * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL is 0.
- */
- retval = -EINVAL;
- if (lp.sched_priority < 0 || lp.sched_priority > MAX_USER_RT_PRIO-1)
- goto out_unlock;
- if ((policy == SCHED_NORMAL) != (lp.sched_priority == 0))
- goto out_unlock;
-
- retval = -EPERM;
- if ((policy == SCHED_FIFO || policy == SCHED_RR) &&
- !capable(CAP_SYS_NICE))
- goto out_unlock;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
- goto out_unlock;
+__setup ("migration_cost=", migration_cost_setup);
- retval = security_task_setscheduler(p, policy, &lp);
- if (retval)
- goto out_unlock;
+/*
+ * Global multiplier (divisor) for migration-cutoff values,
+ * in percentiles. E.g. use a value of 150 to get 1.5 times
+ * longer cache-hot cutoff times.
+ *
+ * (We scale it from 100 to 128 to long long handling easier.)
+ */
- array = p->array;
- if (array)
- deactivate_task(p, task_rq(p));
- retval = 0;
- oldprio = p->prio;
- __setscheduler(p, policy, lp.sched_priority);
- if (array) {
- __activate_task(p, task_rq(p));
- /*
- * Reschedule if we are currently running on this runqueue and
- * our priority decreased, or if we are not currently running on
- * this runqueue and our priority is higher than the current's
- */
- if (task_running(rq, p)) {
- if (p->prio > oldprio)
- resched_task(rq->curr);
- } else if (p->prio < rq->curr->prio)
- resched_task(rq->curr);
- }
+#define MIGRATION_FACTOR_SCALE 128
-out_unlock:
- task_rq_unlock(rq, &flags);
-out_unlock_tasklist:
- read_unlock_irq(&tasklist_lock);
+static unsigned int migration_factor = MIGRATION_FACTOR_SCALE;
-out_nounlock:
- return retval;
+static int __init setup_migration_factor(char *str)
+{
+ get_option(&str, &migration_factor);
+ migration_factor = migration_factor * MIGRATION_FACTOR_SCALE / 100;
+ return 1;
}
-/**
- * sys_sched_setscheduler - set/change the scheduler policy and RT priority
- * @pid: the pid in question.
- * @policy: new policy
- * @param: structure containing the new RT priority.
+__setup("migration_factor=", setup_migration_factor);
+
+/*
+ * Estimated distance of two CPUs, measured via the number of domains
+ * we have to pass for the two CPUs to be in the same span:
*/
-asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
- struct sched_param __user *param)
+static unsigned long domain_distance(int cpu1, int cpu2)
{
- return setscheduler(pid, policy, param);
+ unsigned long distance = 0;
+ struct sched_domain *sd;
+
+ for_each_domain(cpu1, sd) {
+ WARN_ON(!cpu_isset(cpu1, sd->span));
+ if (cpu_isset(cpu2, sd->span))
+ return distance;
+ distance++;
+ }
+ if (distance >= MAX_DOMAIN_DISTANCE) {
+ WARN_ON(1);
+ distance = MAX_DOMAIN_DISTANCE-1;
+ }
+
+ return distance;
}
-/**
- * sys_sched_setparam - set/change the RT priority of a thread
- * @pid: the pid in question.
- * @param: structure containing the new RT priority.
- */
-asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+static unsigned int migration_debug;
+
+static int __init setup_migration_debug(char *str)
{
- return setscheduler(pid, -1, param);
+ get_option(&str, &migration_debug);
+ return 1;
}
-/**
- * sys_sched_getscheduler - get the policy (scheduling class) of a thread
- * @pid: the pid in question.
+__setup("migration_debug=", setup_migration_debug);
+
+/*
+ * Maximum cache-size that the scheduler should try to measure.
+ * Architectures with larger caches should tune this up during
+ * bootup. Gets used in the domain-setup code (i.e. during SMP
+ * bootup).
*/
-asmlinkage long sys_sched_getscheduler(pid_t pid)
+unsigned int max_cache_size;
+
+static int __init setup_max_cache_size(char *str)
{
- int retval = -EINVAL;
- task_t *p;
+ get_option(&str, &max_cache_size);
+ return 1;
+}
- if (pid < 0)
- goto out_nounlock;
+__setup("max_cache_size=", setup_max_cache_size);
- retval = -ESRCH;
- read_lock(&tasklist_lock);
- p = find_process_by_pid(pid);
- if (p) {
- retval = security_task_getscheduler(p);
- if (!retval)
- retval = p->policy;
- }
- read_unlock(&tasklist_lock);
+/*
+ * Dirty a big buffer in a hard-to-predict (for the L2 cache) way. This
+ * is the operation that is timed, so we try to generate unpredictable
+ * cachemisses that still end up filling the L2 cache:
+ */
+static void touch_cache(void *__cache, unsigned long __size)
+{
+ unsigned long size = __size/sizeof(long), chunk1 = size/3,
+ chunk2 = 2*size/3;
+ unsigned long *cache = __cache;
+ int i;
-out_nounlock:
- return retval;
+ for (i = 0; i < size/6; i += 8) {
+ switch (i % 6) {
+ case 0: cache[i]++;
+ case 1: cache[size-1-i]++;
+ case 2: cache[chunk1-i]++;
+ case 3: cache[chunk1+i]++;
+ case 4: cache[chunk2-i]++;
+ case 5: cache[chunk2+i]++;
+ }
+ }
}
-/**
- * sys_sched_getscheduler - get the RT priority of a thread
- * @pid: the pid in question.
- * @param: structure containing the RT priority.
+/*
+ * Measure the cache-cost of one task migration. Returns in units of nsec.
*/
-asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+static unsigned long long measure_one(void *cache, unsigned long size,
+ int source, int target)
{
- struct sched_param lp;
- int retval = -EINVAL;
- task_t *p;
+ cpumask_t mask, saved_mask;
+ unsigned long long t0, t1, t2, t3, cost;
- if (!param || pid < 0)
- goto out_nounlock;
+ saved_mask = current->cpus_allowed;
- read_lock(&tasklist_lock);
- p = find_process_by_pid(pid);
- retval = -ESRCH;
- if (!p)
- goto out_unlock;
+ /*
+ * Flush source caches to RAM and invalidate them:
+ */
+ sched_cacheflush();
- retval = security_task_getscheduler(p);
- if (retval)
- goto out_unlock;
+ /*
+ * Migrate to the source CPU:
+ */
+ mask = cpumask_of_cpu(source);
+ set_cpus_allowed(current, mask);
+ WARN_ON(smp_processor_id() != source);
- lp.sched_priority = p->rt_priority;
- read_unlock(&tasklist_lock);
+ /*
+ * Dirty the working set:
+ */
+ t0 = sched_clock();
+ touch_cache(cache, size);
+ t1 = sched_clock();
/*
- * This one might sleep, we cannot do it with a spinlock held ...
+ * Migrate to the target CPU, dirty the L2 cache and access
+ * the shared buffer. (which represents the working set
+ * of a migrated task.)
*/
- retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+ mask = cpumask_of_cpu(target);
+ set_cpus_allowed(current, mask);
+ WARN_ON(smp_processor_id() != target);
-out_nounlock:
- return retval;
+ t2 = sched_clock();
+ touch_cache(cache, size);
+ t3 = sched_clock();
-out_unlock:
- read_unlock(&tasklist_lock);
- return retval;
+ cost = t1-t0 + t3-t2;
+
+ if (migration_debug >= 2)
+ printk("[%d->%d]: %8Ld %8Ld %8Ld => %10Ld.\n",
+ source, target, t1-t0, t1-t0, t3-t2, cost);
+ /*
+ * Flush target caches to RAM and invalidate them:
+ */
+ sched_cacheflush();
+
+ set_cpus_allowed(current, saved_mask);
+
+ return cost;
}
-/**
- * sys_sched_setaffinity - set the cpu affinity of a process
- * @pid: pid of the process
- * @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to the new cpu mask
+/*
+ * Measure a series of task migrations and return the average
+ * result. Since this code runs early during bootup the system
+ * is 'undisturbed' and the average latency makes sense.
+ *
+ * The algorithm in essence auto-detects the relevant cache-size,
+ * so it will properly detect different cachesizes for different
+ * cache-hierarchies, depending on how the CPUs are connected.
+ *
+ * Architectures can prime the upper limit of the search range via
+ * max_cache_size, otherwise the search range defaults to 20MB...64K.
*/
-asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
- unsigned long __user *user_mask_ptr)
+static unsigned long long
+measure_cost(int cpu1, int cpu2, void *cache, unsigned int size)
{
- cpumask_t new_mask;
- int retval;
- task_t *p;
-
- if (len < sizeof(new_mask))
- return -EINVAL;
+ unsigned long long cost1, cost2;
+ int i;
- if (copy_from_user(&new_mask, user_mask_ptr, sizeof(new_mask)))
- return -EFAULT;
+ /*
+ * Measure the migration cost of 'size' bytes, over an
+ * average of 10 runs:
+ *
+ * (We perturb the cache size by a small (0..4k)
+ * value to compensate size/alignment related artifacts.
+ * We also subtract the cost of the operation done on
+ * the same CPU.)
+ */
+ cost1 = 0;
- lock_cpu_hotplug();
- read_lock(&tasklist_lock);
+ /*
+ * dry run, to make sure we start off cache-cold on cpu1,
+ * and to get any vmalloc pagefaults in advance:
+ */
+ measure_one(cache, size, cpu1, cpu2);
+ for (i = 0; i < ITERATIONS; i++)
+ cost1 += measure_one(cache, size - i*1024, cpu1, cpu2);
- p = find_process_by_pid(pid);
- if (!p) {
- read_unlock(&tasklist_lock);
- unlock_cpu_hotplug();
- return -ESRCH;
- }
+ measure_one(cache, size, cpu2, cpu1);
+ for (i = 0; i < ITERATIONS; i++)
+ cost1 += measure_one(cache, size - i*1024, cpu2, cpu1);
/*
- * It is not safe to call set_cpus_allowed with the
- * tasklist_lock held. We will bump the task_struct's
- * usage count and then drop tasklist_lock.
+ * (We measure the non-migrating [cached] cost on both
+ * cpu1 and cpu2, to handle CPUs with different speeds)
*/
- get_task_struct(p);
- read_unlock(&tasklist_lock);
+ cost2 = 0;
- retval = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
- goto out_unlock;
+ measure_one(cache, size, cpu1, cpu1);
+ for (i = 0; i < ITERATIONS; i++)
+ cost2 += measure_one(cache, size - i*1024, cpu1, cpu1);
- retval = set_cpus_allowed(p, new_mask);
+ measure_one(cache, size, cpu2, cpu2);
+ for (i = 0; i < ITERATIONS; i++)
+ cost2 += measure_one(cache, size - i*1024, cpu2, cpu2);
-out_unlock:
- put_task_struct(p);
- unlock_cpu_hotplug();
- return retval;
+ /*
+ * Get the per-iteration migration cost:
+ */
+ do_div(cost1, 2*ITERATIONS);
+ do_div(cost2, 2*ITERATIONS);
+
+ return cost1 - cost2;
}
-/**
- * sys_sched_getaffinity - get the cpu affinity of a process
- * @pid: pid of the process
- * @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to hold the current cpu mask
- */
-asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
- unsigned long __user *user_mask_ptr)
+static unsigned long long measure_migration_cost(int cpu1, int cpu2)
{
- unsigned int real_len;
- cpumask_t mask;
- int retval;
- task_t *p;
+ unsigned long long max_cost = 0, fluct = 0, avg_fluct = 0;
+ unsigned int max_size, size, size_found = 0;
+ long long cost = 0, prev_cost;
+ void *cache;
- real_len = sizeof(mask);
- if (len < real_len)
- return -EINVAL;
+ /*
+ * Search from max_cache_size*5 down to 64K - the real relevant
+ * cachesize has to lie somewhere inbetween.
+ */
+ if (max_cache_size) {
+ max_size = max(max_cache_size * SEARCH_SCOPE, MIN_CACHE_SIZE);
+ size = max(max_cache_size / SEARCH_SCOPE, MIN_CACHE_SIZE);
+ } else {
+ /*
+ * Since we have no estimation about the relevant
+ * search range
+ */
+ max_size = DEFAULT_CACHE_SIZE * SEARCH_SCOPE;
+ size = MIN_CACHE_SIZE;
+ }
- read_lock(&tasklist_lock);
+ if (!cpu_online(cpu1) || !cpu_online(cpu2)) {
+ printk("cpu %d and %d not both online!\n", cpu1, cpu2);
+ return 0;
+ }
- retval = -ESRCH;
- p = find_process_by_pid(pid);
- if (!p)
- goto out_unlock;
+ /*
+ * Allocate the working set:
+ */
+ cache = vmalloc(max_size);
+ if (!cache) {
+ printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
+ return 1000000; // return 1 msec on very small boxen
+ }
- retval = 0;
- cpus_and(mask, p->cpus_allowed, cpu_possible_map);
+ while (size <= max_size) {
+ prev_cost = cost;
+ cost = measure_cost(cpu1, cpu2, cache, size);
-out_unlock:
- read_unlock(&tasklist_lock);
- if (retval)
- return retval;
- if (copy_to_user(user_mask_ptr, &mask, real_len))
- return -EFAULT;
- return real_len;
+ /*
+ * Update the max:
+ */
+ if (cost > 0) {
+ if (max_cost < cost) {
+ max_cost = cost;
+ size_found = size;
+ }
+ }
+ /*
+ * Calculate average fluctuation, we use this to prevent
+ * noise from triggering an early break out of the loop:
+ */
+ fluct = abs(cost - prev_cost);
+ avg_fluct = (avg_fluct + fluct)/2;
+
+ if (migration_debug)
+ printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n",
+ cpu1, cpu2, size,
+ (long)cost / 1000000,
+ ((long)cost / 100000) % 10,
+ (long)max_cost / 1000000,
+ ((long)max_cost / 100000) % 10,
+ domain_distance(cpu1, cpu2),
+ cost, avg_fluct);
+
+ /*
+ * If we iterated at least 20% past the previous maximum,
+ * and the cost has dropped by more than 20% already,
+ * (taking fluctuations into account) then we assume to
+ * have found the maximum and break out of the loop early:
+ */
+ if (size_found && (size*100 > size_found*SIZE_THRESH))
+ if (cost+avg_fluct <= 0 ||
+ max_cost*100 > (cost+avg_fluct)*COST_THRESH) {
+
+ if (migration_debug)
+ printk("-> found max.\n");
+ break;
+ }
+ /*
+ * Increase the cachesize in 10% steps:
+ */
+ size = size * 10 / 9;
+ }
+
+ if (migration_debug)
+ printk("[%d][%d] working set size found: %d, cost: %Ld\n",
+ cpu1, cpu2, size_found, max_cost);
+
+ vfree(cache);
+
+ /*
+ * A task is considered 'cache cold' if at least 2 times
+ * the worst-case cost of migration has passed.
+ *
+ * (this limit is only listened to if the load-balancing
+ * situation is 'nice' - if there is a large imbalance we
+ * ignore it for the sake of CPU utilization and
+ * processing fairness.)
+ */
+ return 2 * max_cost * migration_factor / MIGRATION_FACTOR_SCALE;
}
-/**
- * sys_sched_yield - yield the current processor to other threads.
- *
- * this function yields the current CPU by moving the calling thread
- * to the expired array. If there are no other threads running on this
- * CPU then this function will return.
- */
-asmlinkage long sys_sched_yield(void)
+static void calibrate_migration_costs(const cpumask_t *cpu_map)
{
- runqueue_t *rq = this_rq_lock();
- prio_array_t *array = current->array;
+ int cpu1 = -1, cpu2 = -1, cpu, orig_cpu = raw_smp_processor_id();
+ unsigned long j0, j1, distance, max_distance = 0;
+ struct sched_domain *sd;
+
+ j0 = jiffies;
/*
- * We implement yielding by moving the task into the expired
- * queue.
- *
- * (special rule: RT tasks will just roundrobin in the active
- * array.)
+ * First pass - calculate the cacheflush times:
+ */
+ for_each_cpu_mask(cpu1, *cpu_map) {
+ for_each_cpu_mask(cpu2, *cpu_map) {
+ if (cpu1 == cpu2)
+ continue;
+ distance = domain_distance(cpu1, cpu2);
+ max_distance = max(max_distance, distance);
+ /*
+ * No result cached yet?
+ */
+ if (migration_cost[distance] == -1LL)
+ migration_cost[distance] =
+ measure_migration_cost(cpu1, cpu2);
+ }
+ }
+ /*
+ * Second pass - update the sched domain hierarchy with
+ * the new cache-hot-time estimations:
*/
- if (likely(!rt_task(current))) {
- dequeue_task(current, array);
- enqueue_task(current, rq->expired);
- } else {
- list_del(¤t->run_list);
- list_add_tail(¤t->run_list, array->queue + current->prio);
+ for_each_cpu_mask(cpu, *cpu_map) {
+ distance = 0;
+ for_each_domain(cpu, sd) {
+ sd->cache_hot_time = migration_cost[distance];
+ distance++;
+ }
}
/*
- * Since we are going to call schedule() anyway, there's
- * no need to preempt:
+ * Print the matrix:
*/
- _raw_spin_unlock(&rq->lock);
- preempt_enable_no_resched();
-
- schedule();
+ if (migration_debug)
+ printk("migration: max_cache_size: %d, cpu: %d MHz:\n",
+ max_cache_size,
+#ifdef CONFIG_X86
+ cpu_khz/1000
+#else
+ -1
+#endif
+ );
+ if (system_state == SYSTEM_BOOTING) {
+ if (num_online_cpus() > 1) {
+ printk("migration_cost=");
+ for (distance = 0; distance <= max_distance; distance++) {
+ if (distance)
+ printk(",");
+ printk("%ld", (long)migration_cost[distance] / 1000);
+ }
+ printk("\n");
+ }
+ }
+ j1 = jiffies;
+ if (migration_debug)
+ printk("migration: %ld seconds\n", (j1-j0)/HZ);
- return 0;
-}
+ /*
+ * Move back to the original CPU. NUMA-Q gets confused
+ * if we migrate to another quad during bootup.
+ */
+ if (raw_smp_processor_id() != orig_cpu) {
+ cpumask_t mask = cpumask_of_cpu(orig_cpu),
+ saved_mask = current->cpus_allowed;
-void __sched __cond_resched(void)
-{
- set_current_state(TASK_RUNNING);
- schedule();
+ set_cpus_allowed(current, mask);
+ set_cpus_allowed(current, saved_mask);
+ }
}
-EXPORT_SYMBOL(__cond_resched);
+#ifdef CONFIG_NUMA
/**
- * yield - yield the current processor to other threads.
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
*
- * this is a shortcut for kernel-space yielding - it marks the
- * thread runnable and calls sys_sched_yield().
- */
-void __sched yield(void)
-{
- set_current_state(TASK_RUNNING);
- sys_sched_yield();
-}
-
-EXPORT_SYMBOL(yield);
-
-/*
- * This task is about to go to sleep on IO. Increment rq->nr_iowait so
- * that process accounting knows that this is a task in IO wait state.
+ * Find the next node to include in a given scheduling domain. Simply
+ * finds the closest node not already in the @used_nodes map.
*
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
+ * Should use nodemask_t.
*/
-void __sched io_schedule(void)
+static int find_next_best_node(int node, unsigned long *used_nodes)
{
- struct runqueue *rq = this_rq();
+ int i, n, val, min_val, best_node = 0;
- atomic_inc(&rq->nr_iowait);
- schedule();
- atomic_dec(&rq->nr_iowait);
-}
+ min_val = INT_MAX;
-EXPORT_SYMBOL(io_schedule);
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ /* Start at @node */
+ n = (node + i) % MAX_NUMNODES;
-long __sched io_schedule_timeout(long timeout)
-{
- struct runqueue *rq = this_rq();
- long ret;
+ if (!nr_cpus_node(n))
+ continue;
- atomic_inc(&rq->nr_iowait);
- ret = schedule_timeout(timeout);
- atomic_dec(&rq->nr_iowait);
- return ret;
-}
+ /* Skip already used nodes */
+ if (test_bit(n, used_nodes))
+ continue;
-/**
- * sys_sched_get_priority_max - return maximum RT priority.
- * @policy: scheduling class.
- *
- * this syscall returns the maximum rt_priority that can be used
- * by a given scheduling class.
- */
-asmlinkage long sys_sched_get_priority_max(int policy)
-{
- int ret = -EINVAL;
+ /* Simple min distance search */
+ val = node_distance(node, n);
- switch (policy) {
- case SCHED_FIFO:
- case SCHED_RR:
- ret = MAX_USER_RT_PRIO-1;
- break;
- case SCHED_NORMAL:
- ret = 0;
- break;
+ if (val < min_val) {
+ min_val = val;
+ best_node = n;
+ }
}
- return ret;
-}
-
-/**
- * sys_sched_get_priority_min - return minimum RT priority.
- * @policy: scheduling class.
- *
- * this syscall returns the minimum rt_priority that can be used
- * by a given scheduling class.
- */
-asmlinkage long sys_sched_get_priority_min(int policy)
-{
- int ret = -EINVAL;
- switch (policy) {
- case SCHED_FIFO:
- case SCHED_RR:
- ret = 1;
- break;
- case SCHED_NORMAL:
- ret = 0;
- }
- return ret;
+ set_bit(best_node, used_nodes);
+ return best_node;
}
/**
- * sys_sched_rr_get_interval - return the default timeslice of a process.
- * @pid: pid of the process.
- * @interval: userspace pointer to the timeslice value.
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @size: number of nodes to include in this span
*
- * this syscall writes the default timeslice value of a given process
- * into the user-space timespec buffer. A value of '0' means infinity.
+ * Given a node, construct a good cpumask for its sched_domain to span. It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
*/
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+static cpumask_t sched_domain_node_span(int node)
{
- int retval = -EINVAL;
- struct timespec t;
- task_t *p;
+ int i;
+ cpumask_t span, nodemask;
+ DECLARE_BITMAP(used_nodes, MAX_NUMNODES);
- if (pid < 0)
- goto out_nounlock;
+ cpus_clear(span);
+ bitmap_zero(used_nodes, MAX_NUMNODES);
- retval = -ESRCH;
- read_lock(&tasklist_lock);
- p = find_process_by_pid(pid);
- if (!p)
- goto out_unlock;
+ nodemask = node_to_cpumask(node);
+ cpus_or(span, span, nodemask);
+ set_bit(node, used_nodes);
- retval = security_task_getscheduler(p);
- if (retval)
- goto out_unlock;
+ for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+ int next_node = find_next_best_node(node, used_nodes);
+ nodemask = node_to_cpumask(next_node);
+ cpus_or(span, span, nodemask);
+ }
- jiffies_to_timespec(p->policy & SCHED_FIFO ?
- 0 : task_timeslice(p), &t);
- read_unlock(&tasklist_lock);
- retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
-out_nounlock:
- return retval;
-out_unlock:
- read_unlock(&tasklist_lock);
- return retval;
+ return span;
}
+#endif
-static inline struct task_struct *eldest_child(struct task_struct *p)
+/*
+ * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
+ * can switch it on easily if needed.
+ */
+#ifdef CONFIG_SCHED_SMT
+static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
+static struct sched_group sched_group_cpus[NR_CPUS];
+static int cpu_to_cpu_group(int cpu)
{
- if (list_empty(&p->children)) return NULL;
- return list_entry(p->children.next,struct task_struct,sibling);
+ return cpu;
}
+#endif
-static inline struct task_struct *older_sibling(struct task_struct *p)
-{
- if (p->sibling.prev==&p->parent->children) return NULL;
- return list_entry(p->sibling.prev,struct task_struct,sibling);
-}
+#ifdef CONFIG_SCHED_MC
+static DEFINE_PER_CPU(struct sched_domain, core_domains);
+static struct sched_group sched_group_core[NR_CPUS];
+#endif
-static inline struct task_struct *younger_sibling(struct task_struct *p)
+#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+static int cpu_to_core_group(int cpu)
{
- if (p->sibling.next==&p->parent->children) return NULL;
- return list_entry(p->sibling.next,struct task_struct,sibling);
+ return first_cpu(cpu_sibling_map[cpu]);
}
-
-static void show_task(task_t * p)
+#elif defined(CONFIG_SCHED_MC)
+static int cpu_to_core_group(int cpu)
{
- task_t *relative;
- unsigned state;
- unsigned long free = 0;
- static const char *stat_nam[] = { "R", "S", "D", "T", "Z", "W" };
-
- printk("%-13.13s ", p->comm);
- state = p->state ? __ffs(p->state) + 1 : 0;
- if (state < ARRAY_SIZE(stat_nam))
- printk(stat_nam[state]);
- else
- printk("?");
-#if (BITS_PER_LONG == 32)
- if (state == TASK_RUNNING)
- printk(" running ");
- else
- printk(" %08lX ", thread_saved_pc(p));
-#else
- if (state == TASK_RUNNING)
- printk(" running task ");
- else
- printk(" %016lx ", thread_saved_pc(p));
-#endif
-#ifdef CONFIG_DEBUG_STACK_USAGE
- {
- unsigned long * n = (unsigned long *) (p->thread_info+1);
- while (!*n)
- n++;
- free = (unsigned long) n - (unsigned long)(p->thread_info+1);
- }
-#endif
- printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
- if ((relative = eldest_child(p)))
- printk("%5d ", relative->pid);
- else
- printk(" ");
- if ((relative = younger_sibling(p)))
- printk("%7d", relative->pid);
- else
- printk(" ");
- if ((relative = older_sibling(p)))
- printk(" %5d", relative->pid);
- else
- printk(" ");
- if (!p->mm)
- printk(" (L-TLB)\n");
- else
- printk(" (NOTLB)\n");
-
- if (state != TASK_RUNNING)
- show_stack(p, NULL);
+ return cpu;
}
-
-void show_state(void)
-{
- task_t *g, *p;
-
-#if (BITS_PER_LONG == 32)
- printk("\n"
- " sibling\n");
- printk(" task PC pid father child younger older\n");
-#else
- printk("\n"
- " sibling\n");
- printk(" task PC pid father child younger older\n");
#endif
- read_lock(&tasklist_lock);
- do_each_thread(g, p) {
- /*
- * reset the NMI-timeout, listing all files on a slow
- * console might take alot of time:
- */
- touch_nmi_watchdog();
- show_task(p);
- } while_each_thread(g, p);
-
- read_unlock(&tasklist_lock);
-}
-void __init init_idle(task_t *idle, int cpu)
+static DEFINE_PER_CPU(struct sched_domain, phys_domains);
+static struct sched_group sched_group_phys[NR_CPUS];
+static int cpu_to_phys_group(int cpu)
{
- runqueue_t *idle_rq = cpu_rq(cpu), *rq = cpu_rq(task_cpu(idle));
- unsigned long flags;
-
- local_irq_save(flags);
- double_rq_lock(idle_rq, rq);
-
- idle_rq->curr = idle_rq->idle = idle;
- deactivate_task(idle, rq);
- idle->array = NULL;
- idle->prio = MAX_PRIO;
- idle->state = TASK_RUNNING;
- set_task_cpu(idle, cpu);
- double_rq_unlock(idle_rq, rq);
- set_tsk_need_resched(idle);
- local_irq_restore(flags);
-
- /* Set the preempt count _outside_ the spinlocks! */
-#ifdef CONFIG_PREEMPT
- idle->thread_info->preempt_count = (idle->lock_depth >= 0);
+#if defined(CONFIG_SCHED_MC)
+ cpumask_t mask = cpu_coregroup_map(cpu);
+ return first_cpu(mask);
+#elif defined(CONFIG_SCHED_SMT)
+ return first_cpu(cpu_sibling_map[cpu]);
#else
- idle->thread_info->preempt_count = 0;
+ return cpu;
#endif
}
+#ifdef CONFIG_NUMA
/*
- * In a system that switches off the HZ timer idle_cpu_mask
- * indicates which cpus entered this state. This is used
- * in the rcu update to wait only for active cpus. For system
- * which do not switch off the HZ timer idle_cpu_mask should
- * always be CPU_MASK_NONE.
+ * The init_sched_build_groups can't handle what we want to do with node
+ * groups, so roll our own. Now each node has its own list of groups which
+ * gets dynamically allocated.
*/
-cpumask_t idle_cpu_mask = CPU_MASK_NONE;
+static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
-#ifdef CONFIG_SMP
-/*
- * This is how migration works:
- *
- * 1) we queue a migration_req_t structure in the source CPU's
- * runqueue and wake up that CPU's migration thread.
- * 2) we down() the locked semaphore => thread blocks.
- * 3) migration thread wakes up (implicitly it forces the migrated
- * thread off the CPU)
- * 4) it gets the migration request and checks whether the migrated
- * task is still in the wrong runqueue.
- * 5) if it's in the wrong runqueue then the migration thread removes
- * it and puts it into the right queue.
- * 6) migration thread up()s the semaphore.
- * 7) we wake up and the migration is done.
- */
+static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static struct sched_group *sched_group_allnodes_bycpu[NR_CPUS];
+
+static int cpu_to_allnodes_group(int cpu)
+{
+ return cpu_to_node(cpu);
+}
+static void init_numa_sched_groups_power(struct sched_group *group_head)
+{
+ struct sched_group *sg = group_head;
+ int j;
+
+ if (!sg)
+ return;
+next_sg:
+ for_each_cpu_mask(j, sg->cpumask) {
+ struct sched_domain *sd;
+
+ sd = &per_cpu(phys_domains, j);
+ if (j != first_cpu(sd->groups->cpumask)) {
+ /*
+ * Only add "power" once for each
+ * physical package.
+ */
+ continue;
+ }
+
+ sg->cpu_power += sd->groups->cpu_power;
+ }
+ sg = sg->next;
+ if (sg != group_head)
+ goto next_sg;
+}
+#endif
/*
- * Change a given task's CPU affinity. Migrate the thread to a
- * proper CPU and schedule it away if the CPU it's executing on
- * is removed from the allowed bitmask.
- *
- * NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely. The
- * call is not atomic; no spinlocks may be held.
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
*/
-int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+void build_sched_domains(const cpumask_t *cpu_map)
{
- unsigned long flags;
- int ret = 0;
- migration_req_t req;
- runqueue_t *rq;
+ int i;
+#ifdef CONFIG_NUMA
+ struct sched_group **sched_group_nodes = NULL;
+ struct sched_group *sched_group_allnodes = NULL;
- rq = task_rq_lock(p, &flags);
- if (any_online_cpu(new_mask) == NR_CPUS) {
- ret = -EINVAL;
- goto out;
+ /*
+ * Allocate the per-node list of sched groups
+ */
+ sched_group_nodes = kmalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
+ GFP_ATOMIC);
+ if (!sched_group_nodes) {
+ printk(KERN_WARNING "Can not alloc sched group node list\n");
+ return;
}
+ sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
+#endif
- if (__set_cpus_allowed(p, new_mask, &req)) {
- /* Need help from migration thread: drop lock and wait. */
- task_rq_unlock(rq, &flags);
- wake_up_process(rq->migration_thread);
- wait_for_completion(&req.done);
- return 0;
- }
-out:
- task_rq_unlock(rq, &flags);
- return ret;
-}
+ /*
+ * Set up domains for cpus specified by the cpu_map.
+ */
+ for_each_cpu_mask(i, *cpu_map) {
+ int group;
+ struct sched_domain *sd = NULL, *p;
+ cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
-EXPORT_SYMBOL_GPL(set_cpus_allowed);
+ cpus_and(nodemask, nodemask, *cpu_map);
-/* Move (not current) task off this cpu, onto dest cpu. */
-static void move_task_away(struct task_struct *p, int dest_cpu)
-{
- runqueue_t *rq_dest;
+#ifdef CONFIG_NUMA
+ if (cpus_weight(*cpu_map)
+ > SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
+ if (!sched_group_allnodes) {
+ sched_group_allnodes
+ = kmalloc(sizeof(struct sched_group)
+ * MAX_NUMNODES,
+ GFP_KERNEL);
+ if (!sched_group_allnodes) {
+ printk(KERN_WARNING
+ "Can not alloc allnodes sched group\n");
+ break;
+ }
+ sched_group_allnodes_bycpu[i]
+ = sched_group_allnodes;
+ }
+ sd = &per_cpu(allnodes_domains, i);
+ *sd = SD_ALLNODES_INIT;
+ sd->span = *cpu_map;
+ group = cpu_to_allnodes_group(i);
+ sd->groups = &sched_group_allnodes[group];
+ p = sd;
+ } else
+ p = NULL;
- rq_dest = cpu_rq(dest_cpu);
+ sd = &per_cpu(node_domains, i);
+ *sd = SD_NODE_INIT;
+ sd->span = sched_domain_node_span(cpu_to_node(i));
+ sd->parent = p;
+ cpus_and(sd->span, sd->span, *cpu_map);
+#endif
- double_rq_lock(this_rq(), rq_dest);
- if (task_cpu(p) != smp_processor_id())
- goto out; /* Already moved */
+ p = sd;
+ sd = &per_cpu(phys_domains, i);
+ group = cpu_to_phys_group(i);
+ *sd = SD_CPU_INIT;
+ sd->span = nodemask;
+ sd->parent = p;
+ sd->groups = &sched_group_phys[group];
+
+#ifdef CONFIG_SCHED_MC
+ p = sd;
+ sd = &per_cpu(core_domains, i);
+ group = cpu_to_core_group(i);
+ *sd = SD_MC_INIT;
+ sd->span = cpu_coregroup_map(i);
+ cpus_and(sd->span, sd->span, *cpu_map);
+ sd->parent = p;
+ sd->groups = &sched_group_core[group];
+#endif
- set_task_cpu(p, dest_cpu);
- if (p->array) {
- deactivate_task(p, this_rq());
- activate_task(p, rq_dest);
- if (p->prio < rq_dest->curr->prio)
- resched_task(rq_dest->curr);
+#ifdef CONFIG_SCHED_SMT
+ p = sd;
+ sd = &per_cpu(cpu_domains, i);
+ group = cpu_to_cpu_group(i);
+ *sd = SD_SIBLING_INIT;
+ sd->span = cpu_sibling_map[i];
+ cpus_and(sd->span, sd->span, *cpu_map);
+ sd->parent = p;
+ sd->groups = &sched_group_cpus[group];
+#endif
}
- p->timestamp = rq_dest->timestamp_last_tick;
-out:
- double_rq_unlock(this_rq(), rq_dest);
-}
+#ifdef CONFIG_SCHED_SMT
+ /* Set up CPU (sibling) groups */
+ for_each_cpu_mask(i, *cpu_map) {
+ cpumask_t this_sibling_map = cpu_sibling_map[i];
+ cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
+ if (i != first_cpu(this_sibling_map))
+ continue;
-/*
- * migration_thread - this is a highprio system thread that performs
- * thread migration by bumping thread off CPU then 'pushing' onto
- * another runqueue.
- */
-static int migration_thread(void * data)
-{
- runqueue_t *rq;
- int cpu = (long)data;
+ init_sched_build_groups(sched_group_cpus, this_sibling_map,
+ &cpu_to_cpu_group);
+ }
+#endif
- rq = cpu_rq(cpu);
- BUG_ON(rq->migration_thread != current);
+#ifdef CONFIG_SCHED_MC
+ /* Set up multi-core groups */
+ for_each_cpu_mask(i, *cpu_map) {
+ cpumask_t this_core_map = cpu_coregroup_map(i);
+ cpus_and(this_core_map, this_core_map, *cpu_map);
+ if (i != first_cpu(this_core_map))
+ continue;
+ init_sched_build_groups(sched_group_core, this_core_map,
+ &cpu_to_core_group);
+ }
+#endif
- while (!kthread_should_stop()) {
- struct list_head *head;
- migration_req_t *req;
- if (current->flags & PF_FREEZE)
- refrigerator(PF_FREEZE);
+ /* Set up physical groups */
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ cpumask_t nodemask = node_to_cpumask(i);
- spin_lock_irq(&rq->lock);
- head = &rq->migration_queue;
- current->state = TASK_INTERRUPTIBLE;
- if (list_empty(head)) {
- spin_unlock_irq(&rq->lock);
- schedule();
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask))
+ continue;
+
+ init_sched_build_groups(sched_group_phys, nodemask,
+ &cpu_to_phys_group);
+ }
+
+#ifdef CONFIG_NUMA
+ /* Set up node groups */
+ if (sched_group_allnodes)
+ init_sched_build_groups(sched_group_allnodes, *cpu_map,
+ &cpu_to_allnodes_group);
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ /* Set up node groups */
+ struct sched_group *sg, *prev;
+ cpumask_t nodemask = node_to_cpumask(i);
+ cpumask_t domainspan;
+ cpumask_t covered = CPU_MASK_NONE;
+ int j;
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask)) {
+ sched_group_nodes[i] = NULL;
continue;
}
- req = list_entry(head->next, migration_req_t, list);
- list_del_init(head->next);
- spin_unlock(&rq->lock);
- move_task_away(req->task,
- any_online_cpu(req->task->cpus_allowed));
- local_irq_enable();
- complete(&req->done);
+ domainspan = sched_domain_node_span(i);
+ cpus_and(domainspan, domainspan, *cpu_map);
+
+ sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+ sched_group_nodes[i] = sg;
+ for_each_cpu_mask(j, nodemask) {
+ struct sched_domain *sd;
+ sd = &per_cpu(node_domains, j);
+ sd->groups = sg;
+ if (sd->groups == NULL) {
+ /* Turn off balancing if we have no groups */
+ sd->flags = 0;
+ }
+ }
+ if (!sg) {
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", i);
+ continue;
+ }
+ sg->cpu_power = 0;
+ sg->cpumask = nodemask;
+ cpus_or(covered, covered, nodemask);
+ prev = sg;
+
+ for (j = 0; j < MAX_NUMNODES; j++) {
+ cpumask_t tmp, notcovered;
+ int n = (i + j) % MAX_NUMNODES;
+
+ cpus_complement(notcovered, covered);
+ cpus_and(tmp, notcovered, *cpu_map);
+ cpus_and(tmp, tmp, domainspan);
+ if (cpus_empty(tmp))
+ break;
+
+ nodemask = node_to_cpumask(n);
+ cpus_and(tmp, tmp, nodemask);
+ if (cpus_empty(tmp))
+ continue;
+
+ sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+ if (!sg) {
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", j);
+ break;
+ }
+ sg->cpu_power = 0;
+ sg->cpumask = tmp;
+ cpus_or(covered, covered, tmp);
+ prev->next = sg;
+ prev = sg;
+ }
+ prev->next = sched_group_nodes[i];
}
- return 0;
-}
+#endif
-#ifdef CONFIG_HOTPLUG_CPU
-/* migrate_all_tasks - function to migrate all the tasks from the
- * current cpu caller must have already scheduled this to the target
- * cpu via set_cpus_allowed. Machine is stopped. */
-void migrate_all_tasks(void)
+ /* Calculate CPU power for physical packages and nodes */
+ for_each_cpu_mask(i, *cpu_map) {
+ int power;
+ struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+ sd = &per_cpu(cpu_domains, i);
+ power = SCHED_LOAD_SCALE;
+ sd->groups->cpu_power = power;
+#endif
+#ifdef CONFIG_SCHED_MC
+ sd = &per_cpu(core_domains, i);
+ power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
+ * SCHED_LOAD_SCALE / 10;
+ sd->groups->cpu_power = power;
+
+ sd = &per_cpu(phys_domains, i);
+
+ /*
+ * This has to be < 2 * SCHED_LOAD_SCALE
+ * Lets keep it SCHED_LOAD_SCALE, so that
+ * while calculating NUMA group's cpu_power
+ * we can simply do
+ * numa_group->cpu_power += phys_group->cpu_power;
+ *
+ * See "only add power once for each physical pkg"
+ * comment below
+ */
+ sd->groups->cpu_power = SCHED_LOAD_SCALE;
+#else
+ sd = &per_cpu(phys_domains, i);
+ power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
+ (cpus_weight(sd->groups->cpumask)-1) / 10;
+ sd->groups->cpu_power = power;
+#endif
+ }
+
+#ifdef CONFIG_NUMA
+ for (i = 0; i < MAX_NUMNODES; i++)
+ init_numa_sched_groups_power(sched_group_nodes[i]);
+
+ init_numa_sched_groups_power(sched_group_allnodes);
+#endif
+
+ /* Attach the domains */
+ for_each_cpu_mask(i, *cpu_map) {
+ struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+ sd = &per_cpu(cpu_domains, i);
+#elif defined(CONFIG_SCHED_MC)
+ sd = &per_cpu(core_domains, i);
+#else
+ sd = &per_cpu(phys_domains, i);
+#endif
+ cpu_attach_domain(sd, i);
+ }
+ /*
+ * Tune cache-hot values:
+ */
+ calibrate_migration_costs(cpu_map);
+}
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ */
+static void arch_init_sched_domains(const cpumask_t *cpu_map)
{
- struct task_struct *tsk, *t;
- int dest_cpu, src_cpu;
- unsigned int node;
+ cpumask_t cpu_default_map;
- /* We're nailed to this CPU. */
- src_cpu = smp_processor_id();
+ /*
+ * Setup mask for cpus without special case scheduling requirements.
+ * For now this just excludes isolated cpus, but could be used to
+ * exclude other special cases in the future.
+ */
+ cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
- /* Not required, but here for neatness. */
- write_lock(&tasklist_lock);
+ build_sched_domains(&cpu_default_map);
+}
- /* watch out for per node tasks, let's stay on this node */
- node = cpu_to_node(src_cpu);
+static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
+{
+#ifdef CONFIG_NUMA
+ int i;
+ int cpu;
- do_each_thread(t, tsk) {
- cpumask_t mask;
- if (tsk == current)
- continue;
+ for_each_cpu_mask(cpu, *cpu_map) {
+ struct sched_group *sched_group_allnodes
+ = sched_group_allnodes_bycpu[cpu];
+ struct sched_group **sched_group_nodes
+ = sched_group_nodes_bycpu[cpu];
+
+ if (sched_group_allnodes) {
+ kfree(sched_group_allnodes);
+ sched_group_allnodes_bycpu[cpu] = NULL;
+ }
- if (task_cpu(tsk) != src_cpu)
+ if (!sched_group_nodes)
continue;
- /* Figure out where this task should go (attempting to
- * keep it on-node), and check if it can be migrated
- * as-is. NOTE that kernel threads bound to more than
- * one online cpu will be migrated. */
- mask = node_to_cpumask(node);
- cpus_and(mask, mask, tsk->cpus_allowed);
- dest_cpu = any_online_cpu(mask);
- if (dest_cpu == NR_CPUS)
- dest_cpu = any_online_cpu(tsk->cpus_allowed);
- if (dest_cpu == NR_CPUS) {
- cpus_clear(tsk->cpus_allowed);
- cpus_complement(tsk->cpus_allowed);
- dest_cpu = any_online_cpu(tsk->cpus_allowed);
-
- /* Don't tell them about moving exiting tasks
- or kernel threads (both mm NULL), since
- they never leave kernel. */
- if (tsk->mm && printk_ratelimit())
- printk(KERN_INFO "process %d (%s) no "
- "longer affine to cpu%d\n",
- tsk->pid, tsk->comm, src_cpu);
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ cpumask_t nodemask = node_to_cpumask(i);
+ struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask))
+ continue;
+
+ if (sg == NULL)
+ continue;
+ sg = sg->next;
+next_sg:
+ oldsg = sg;
+ sg = sg->next;
+ kfree(oldsg);
+ if (oldsg != sched_group_nodes[i])
+ goto next_sg;
}
+ kfree(sched_group_nodes);
+ sched_group_nodes_bycpu[cpu] = NULL;
+ }
+#endif
+}
- move_task_away(tsk, dest_cpu);
- } while_each_thread(t, tsk);
+/*
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const cpumask_t *cpu_map)
+{
+ int i;
- write_unlock(&tasklist_lock);
+ for_each_cpu_mask(i, *cpu_map)
+ cpu_attach_domain(NULL, i);
+ synchronize_sched();
+ arch_destroy_sched_domains(cpu_map);
}
-#endif /* CONFIG_HOTPLUG_CPU */
/*
- * migration_call - callback that gets triggered when a CPU is added.
- * Here we can start up the necessary migration thread for the new CPU.
+ * Partition sched domains as specified by the cpumasks below.
+ * This attaches all cpus from the cpumasks to the NULL domain,
+ * waits for a RCU quiescent period, recalculates sched
+ * domain information and then attaches them back to the
+ * correct sched domains
+ * Call with hotplug lock held
*/
-static int migration_call(struct notifier_block *nfb, unsigned long action,
- void *hcpu)
+void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
{
- int cpu = (long)hcpu;
- struct task_struct *p;
- struct runqueue *rq;
- unsigned long flags;
+ cpumask_t change_map;
+
+ cpus_and(*partition1, *partition1, cpu_online_map);
+ cpus_and(*partition2, *partition2, cpu_online_map);
+ cpus_or(change_map, *partition1, *partition2);
+
+ /* Detach sched domains from all of the affected cpus */
+ detach_destroy_domains(&change_map);
+ if (!cpus_empty(*partition1))
+ build_sched_domains(partition1);
+ if (!cpus_empty(*partition2))
+ build_sched_domains(partition2);
+}
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Force a reinitialization of the sched domains hierarchy. The domains
+ * and groups cannot be updated in place without racing with the balancing
+ * code, so we temporarily attach all running cpus to the NULL domain
+ * which will prevent rebalancing while the sched domains are recalculated.
+ */
+static int update_sched_domains(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
switch (action) {
case CPU_UP_PREPARE:
- p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
- if (IS_ERR(p))
- return NOTIFY_BAD;
- kthread_bind(p, cpu);
- /* Must be high prio: stop_machine expects to yield to it. */
- rq = task_rq_lock(p, &flags);
- __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
- task_rq_unlock(rq, &flags);
- cpu_rq(cpu)->migration_thread = p;
- break;
- case CPU_ONLINE:
- /* Strictly unneccessary, as first user will wake it. */
- wake_up_process(cpu_rq(cpu)->migration_thread);
- break;
-#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DOWN_PREPARE:
+ detach_destroy_domains(&cpu_online_map);
+ return NOTIFY_OK;
+
case CPU_UP_CANCELED:
- /* Unbind it from offline cpu so it can run. Fall thru. */
- kthread_bind(cpu_rq(cpu)->migration_thread,smp_processor_id());
+ case CPU_DOWN_FAILED:
+ case CPU_ONLINE:
case CPU_DEAD:
- kthread_stop(cpu_rq(cpu)->migration_thread);
- cpu_rq(cpu)->migration_thread = NULL;
- BUG_ON(cpu_rq(cpu)->nr_running != 0);
- break;
-#endif
+ /*
+ * Fall through and re-initialise the domains.
+ */
+ break;
+ default:
+ return NOTIFY_DONE;
}
+
+ /* The hotplug lock is already held by cpu_up/cpu_down */
+ arch_init_sched_domains(&cpu_online_map);
+
return NOTIFY_OK;
}
+#endif
-static struct notifier_block __devinitdata migration_notifier = {
- .notifier_call = migration_call,
-};
-
-int __init migration_init(void)
+void __init sched_init_smp(void)
{
- void *cpu = (void *)(long)smp_processor_id();
- /* Start one for boot CPU. */
- migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
- migration_call(&migration_notifier, CPU_ONLINE, cpu);
- register_cpu_notifier(&migration_notifier);
- return 0;
+ lock_cpu_hotplug();
+ arch_init_sched_domains(&cpu_online_map);
+ unlock_cpu_hotplug();
+ /* XXX: Theoretical race here - CPU may be hotplugged now */
+ hotcpu_notifier(update_sched_domains, 0);
}
-#endif
+#else
+void __init sched_init_smp(void)
+{
+}
+#endif /* CONFIG_SMP */
-/*
- * The 'big kernel lock'
- *
- * This spinlock is taken and released recursively by lock_kernel()
- * and unlock_kernel(). It is transparently dropped and reaquired
- * over schedule(). It is used to protect legacy code that hasn't
- * been migrated to a proper locking design yet.
- *
- * Don't use in new code.
- *
- * Note: spinlock debugging needs this even on !CONFIG_SMP.
- */
-spinlock_t kernel_flag __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
-EXPORT_SYMBOL(kernel_flag);
+int in_sched_functions(unsigned long addr)
+{
+ /* Linker adds these: start and end of __sched functions */
+ extern char __sched_text_start[], __sched_text_end[];
+ return in_lock_functions(addr) ||
+ (addr >= (unsigned long)__sched_text_start
+ && addr < (unsigned long)__sched_text_end);
+}
void __init sched_init(void)
{
runqueue_t *rq;
int i, j, k;
- for (i = 0; i < NR_CPUS; i++) {
+ for_each_possible_cpu(i) {
prio_array_t *array;
rq = cpu_rq(i);
+ spin_lock_init(&rq->lock);
+ rq->nr_running = 0;
rq->active = rq->arrays;
rq->expired = rq->arrays + 1;
rq->best_expired_prio = MAX_PRIO;
- spin_lock_init(&rq->lock);
+#ifdef CONFIG_SMP
+ rq->sd = NULL;
+ for (j = 1; j < 3; j++)
+ rq->cpu_load[j] = 0;
+ rq->active_balance = 0;
+ rq->push_cpu = 0;
+ rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
+ rq->cpu = i;
+#endif
atomic_set(&rq->nr_iowait, 0);
- nr_running_init(rq);
+#ifdef CONFIG_VSERVER_HARDCPU
+ INIT_LIST_HEAD(&rq->hold_queue);
+#endif
for (j = 0; j < 2; j++) {
array = rq->arrays + j;
__set_bit(MAX_PRIO, array->bitmap);
}
}
- /*
- * We have to do a little magic to get the first
- * thread right in SMP mode.
- */
- rq = this_rq();
- rq->curr = current;
- rq->idle = current;
- set_task_cpu(current, smp_processor_id());
- wake_up_forked_process(current);
-
- init_timers();
/*
* The boot idle thread does lazy MMU switching as well:
*/
atomic_inc(&init_mm.mm_count);
enter_lazy_tlb(&init_mm, current);
+
+ /*
+ * Make us the idle thread. Technically, schedule() should not be
+ * called from this thread, however somewhere below it might be,
+ * but because we are the idle thread, we just pick up running again
+ * when this runqueue becomes "idle".
+ */
+ init_idle(current, smp_processor_id());
}
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
static unsigned long prev_jiffy; /* ratelimiting */
if ((in_atomic() || irqs_disabled()) &&
- system_state == SYSTEM_RUNNING) {
+ system_state == SYSTEM_RUNNING && !oops_in_progress) {
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
- printk(KERN_ERR "Debug: sleeping function called from invalid"
+ printk(KERN_ERR "BUG: sleeping function called from invalid"
" context at %s:%d\n", file, line);
printk("in_atomic():%d, irqs_disabled():%d\n",
in_atomic(), irqs_disabled());
EXPORT_SYMBOL(__might_sleep);
#endif
+#ifdef CONFIG_MAGIC_SYSRQ
+void normalize_rt_tasks(void)
+{
+ struct task_struct *p;
+ prio_array_t *array;
+ unsigned long flags;
+ runqueue_t *rq;
+
+ read_lock_irq(&tasklist_lock);
+ for_each_process (p) {
+ if (!rt_task(p))
+ continue;
+
+ rq = task_rq_lock(p, &flags);
+
+ array = p->array;
+ if (array)
+ deactivate_task(p, task_rq(p));
+ __setscheduler(p, SCHED_NORMAL, 0);
+ if (array) {
+ vx_activate_task(p);
+ __activate_task(p, task_rq(p));
+ resched_task(rq->curr);
+ }
+
+ task_rq_unlock(rq, &flags);
+ }
+ read_unlock_irq(&tasklist_lock);
+}
+
+#endif /* CONFIG_MAGIC_SYSRQ */
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
+#ifdef CONFIG_IA64
/*
- * This could be a long-held lock. If another CPU holds it for a long time,
- * and that CPU is not asked to reschedule then *this* CPU will spin on the
- * lock for a long time, even if *this* CPU is asked to reschedule.
+ * These functions are only useful for the IA64 MCA handling.
*
- * So what we do here, in the slow (contended) path is to spin on the lock by
- * hand while permitting preemption.
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
*
- * Called inside preempt_disable().
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*/
-void __sched __preempt_spin_lock(spinlock_t *lock)
+task_t *curr_task(int cpu)
{
- if (preempt_count() > 1) {
- _raw_spin_lock(lock);
- return;
- }
- do {
- preempt_enable();
- while (spin_is_locked(lock))
- cpu_relax();
- preempt_disable();
- } while (!_raw_spin_trylock(lock));
+ return cpu_curr(cpu);
}
-EXPORT_SYMBOL(__preempt_spin_lock);
-
-void __sched __preempt_write_lock(rwlock_t *lock)
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack. It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner. This function
+ * must be called with all CPU's synchronized, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, task_t *p)
{
- if (preempt_count() > 1) {
- _raw_write_lock(lock);
- return;
- }
-
- do {
- preempt_enable();
- while (rwlock_is_locked(lock))
- cpu_relax();
- preempt_disable();
- } while (!_raw_write_trylock(lock));
+ cpu_curr(cpu) = p;
}
-EXPORT_SYMBOL(__preempt_write_lock);
-#endif /* defined(CONFIG_SMP) && defined(CONFIG_PREEMPT) */
+#endif
git://git.onelab.eu / linux-2.6.git / blobdiff